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
2026-03-17 17:32:03 +01:00
committed by GitHub
parent ad36210e45
commit 0fca6db79c
37 changed files with 1758 additions and 788 deletions
@@ -11,7 +11,7 @@ from django.db import transaction
import pytest
from core import factories
from core.services.search_indexers import SearchIndexer
from core.services.search_indexers import FindDocumentIndexer
@pytest.mark.django_db
@@ -19,7 +19,7 @@ from core.services.search_indexers import SearchIndexer
def test_index():
"""Test the command `index` that run the Find app indexer for all the available documents."""
user = factories.UserFactory()
indexer = SearchIndexer()
indexer = FindDocumentIndexer()
with transaction.atomic():
doc = factories.DocumentFactory()
@@ -36,7 +36,7 @@ def test_index():
str(no_title_doc.path): {"users": [user.sub]},
}
with mock.patch.object(SearchIndexer, "push") as mock_push:
with mock.patch.object(FindDocumentIndexer, "push") as mock_push:
call_command("index")
push_call_args = [call.args[0] for call in mock_push.call_args_list]
+3 -5
View File
@@ -39,12 +39,10 @@ def indexer_settings_fixture(settings):
get_document_indexer.cache_clear()
settings.SEARCH_INDEXER_CLASS = "core.services.search_indexers.SearchIndexer"
settings.SEARCH_INDEXER_CLASS = "core.services.search_indexers.FindDocumentIndexer"
settings.SEARCH_INDEXER_SECRET = "ThisIsAKeyForTest"
settings.SEARCH_INDEXER_URL = "http://localhost:8081/api/v1.0/documents/index/"
settings.SEARCH_INDEXER_QUERY_URL = (
"http://localhost:8081/api/v1.0/documents/search/"
)
settings.INDEXING_URL = "http://localhost:8081/api/v1.0/documents/index/"
settings.SEARCH_URL = "http://localhost:8081/api/v1.0/documents/search/"
settings.SEARCH_INDEXER_COUNTDOWN = 1
yield settings
@@ -16,7 +16,16 @@ fake = Faker()
pytestmark = pytest.mark.django_db
def test_api_documents_list_filter_and_access_rights():
@pytest.mark.parametrize(
"title_search_field",
# for integration with indexer search we must have
# the same filtering behaviour with "q" and "title" parameters
[
("title"),
("q"),
],
)
def test_api_documents_list_filter_and_access_rights(title_search_field):
"""Filtering on querystring parameters should respect access rights."""
user = factories.UserFactory()
client = APIClient()
@@ -76,7 +85,7 @@ def test_api_documents_list_filter_and_access_rights():
filters = {
"link_reach": random.choice([None, *models.LinkReachChoices.values]),
"title": random.choice([None, *word_list]),
title_search_field: random.choice([None, *word_list]),
"favorite": random.choice([None, True, False]),
"creator": random.choice([None, user, other_user]),
"ordering": random.choice(
@@ -59,6 +59,7 @@ def test_api_documents_retrieve_anonymous_public_standalone():
"partial_update": document.link_role == "editor",
"restore": False,
"retrieve": True,
"search": True,
"tree": True,
"update": document.link_role == "editor",
"versions_destroy": False,
@@ -136,6 +137,7 @@ def test_api_documents_retrieve_anonymous_public_parent():
"partial_update": grand_parent.link_role == "editor",
"restore": False,
"retrieve": True,
"search": True,
"tree": True,
"update": grand_parent.link_role == "editor",
"versions_destroy": False,
@@ -246,6 +248,7 @@ def test_api_documents_retrieve_authenticated_unrelated_public_or_authenticated(
"partial_update": document.link_role == "editor",
"restore": False,
"retrieve": True,
"search": True,
"tree": True,
"update": document.link_role == "editor",
"versions_destroy": False,
@@ -330,6 +333,7 @@ def test_api_documents_retrieve_authenticated_public_or_authenticated_parent(rea
"partial_update": grand_parent.link_role == "editor",
"restore": False,
"retrieve": True,
"search": True,
"tree": True,
"update": grand_parent.link_role == "editor",
"versions_destroy": False,
@@ -529,6 +533,7 @@ def test_api_documents_retrieve_authenticated_related_parent():
"partial_update": access.role not in ["reader", "commenter"],
"restore": access.role == "owner",
"retrieve": True,
"search": True,
"tree": True,
"update": access.role not in ["reader", "commenter"],
"versions_destroy": access.role in ["administrator", "owner"],
@@ -1,46 +1,31 @@
"""
Tests for Documents API endpoint in impress's core app: list
Tests for Documents API endpoint in impress's core app: search
"""
import random
from json import loads as json_loads
from django.test import RequestFactory
from unittest import mock
import pytest
import responses
from faker import Faker
from rest_framework import response as drf_response
from rest_framework.test import APIClient
from core import factories, models
from core import factories
from core.services.search_indexers import get_document_indexer
fake = Faker()
pytestmark = pytest.mark.django_db
def build_search_url(**kwargs):
"""Build absolute uri for search endpoint with ORDERED query arguments"""
return (
RequestFactory()
.get("/api/v1.0/documents/search/", dict(sorted(kwargs.items())))
.build_absolute_uri()
)
@pytest.mark.parametrize("role", models.LinkRoleChoices.values)
@pytest.mark.parametrize("reach", models.LinkReachChoices.values)
@mock.patch("core.services.search_indexers.FindDocumentIndexer.search_query")
@responses.activate
def test_api_documents_search_anonymous(reach, role, indexer_settings):
def test_api_documents_search_anonymous(search_query, indexer_settings):
"""
Anonymous users should not be allowed to search documents whatever the
link reach and link role
Anonymous users should be allowed to search documents with Find.
"""
indexer_settings.SEARCH_INDEXER_QUERY_URL = "http://find/api/v1.0/search"
indexer_settings.SEARCH_URL = "http://find/api/v1.0/search"
factories.DocumentFactory(link_reach=reach, link_role=role)
# Find response
# mock Find response
responses.add(
responses.POST,
"http://find/api/v1.0/search",
@@ -48,7 +33,22 @@ def test_api_documents_search_anonymous(reach, role, indexer_settings):
status=200,
)
response = APIClient().get("/api/v1.0/documents/search/", data={"q": "alpha"})
q = "alpha"
response = APIClient().get("/api/v1.0/documents/search/", data={"q": q})
assert search_query.call_count == 1
assert search_query.call_args[1] == {
"data": {
"q": q,
"visited": [],
"services": ["docs"],
"nb_results": 50,
"order_by": "updated_at",
"order_direction": "desc",
"path": None,
},
"token": None,
}
assert response.status_code == 200
assert response.json() == {
@@ -59,64 +59,121 @@ def test_api_documents_search_anonymous(reach, role, indexer_settings):
}
def test_api_documents_search_endpoint_is_none(indexer_settings):
@mock.patch("core.api.viewsets.DocumentViewSet.list")
def test_api_documents_search_fall_back_on_search_list(mock_list, indexer_settings):
"""
Missing SEARCH_INDEXER_QUERY_URL, so the indexer is not properly configured.
Should fallback on title filter
When indexer is not configured and no path is provided,
should fall back on list method
"""
indexer_settings.SEARCH_INDEXER_QUERY_URL = None
indexer_settings.SEARCH_URL = None
assert get_document_indexer() is None
user = factories.UserFactory()
document = factories.DocumentFactory(title="alpha")
access = factories.UserDocumentAccessFactory(document=document, user=user)
client = APIClient()
client.force_login(user)
response = client.get("/api/v1.0/documents/search/", data={"q": "alpha"})
assert response.status_code == 200
content = response.json()
results = content.pop("results")
assert content == {
"count": 1,
mocked_response = {
"count": 0,
"next": None,
"previous": None,
"results": [{"title": "mocked list result"}],
}
assert len(results) == 1
assert results[0] == {
"id": str(document.id),
"abilities": document.get_abilities(user),
"ancestors_link_reach": None,
"ancestors_link_role": None,
"computed_link_reach": document.computed_link_reach,
"computed_link_role": document.computed_link_role,
"created_at": document.created_at.isoformat().replace("+00:00", "Z"),
"creator": str(document.creator.id),
"depth": 1,
"excerpt": document.excerpt,
"link_reach": document.link_reach,
"link_role": document.link_role,
"nb_accesses_ancestors": 1,
"nb_accesses_direct": 1,
"numchild": 0,
"path": document.path,
"title": document.title,
"updated_at": document.updated_at.isoformat().replace("+00:00", "Z"),
"deleted_at": None,
"user_role": access.role,
mock_list.return_value = drf_response.Response(mocked_response)
q = "alpha"
response = client.get("/api/v1.0/documents/search/", data={"q": q})
assert mock_list.call_count == 1
assert mock_list.call_args[0][0].GET.get("q") == q
assert response.json() == mocked_response
@mock.patch("core.api.viewsets.DocumentViewSet._list_descendants")
def test_api_documents_search_fallback_on_search_list_sub_docs(
mock_list_descendants, indexer_settings
):
"""
When indexer is not configured and path parameter is provided,
should call _list_descendants() method
"""
indexer_settings.SEARCH_URL = "http://find/api/v1.0/search"
assert get_document_indexer() is not None
user = factories.UserFactory()
client = APIClient()
client.force_login(user)
parent = factories.DocumentFactory(title="parent", users=[user])
mocked_response = {
"count": 0,
"next": None,
"previous": None,
"results": [{"title": "mocked _list_descendants result"}],
}
mock_list_descendants.return_value = drf_response.Response(mocked_response)
q = "alpha"
response = client.get(
"/api/v1.0/documents/search/", data={"q": q, "path": parent.path}
)
assert mock_list_descendants.call_count == 1
assert mock_list_descendants.call_args[0][0].GET.get("q") == q
assert mock_list_descendants.call_args[0][0].GET.get("path") == parent.path
assert response.json() == mocked_response
@mock.patch("core.api.viewsets.DocumentViewSet._title_search")
def test_api_documents_search_indexer_crashes(mock_title_search, indexer_settings):
"""
When indexer is configured but crashes -> falls back on title_search
"""
# indexer is properly configured
indexer_settings.SEARCH_URL = None
assert get_document_indexer() is None
# but returns an error when the query is sent
responses.add(
responses.POST,
"http://find/api/v1.0/search",
json=[{"error": "Some indexer error"}],
status=404,
)
user = factories.UserFactory()
client = APIClient()
client.force_login(user)
mocked_response = {
"count": 0,
"next": None,
"previous": None,
"results": [{"title": "mocked title_search result"}],
}
mock_title_search.return_value = drf_response.Response(mocked_response)
parent = factories.DocumentFactory(title="parent", users=[user])
q = "alpha"
response = client.get(
"/api/v1.0/documents/search/", data={"q": "alpha", "path": parent.path}
)
# the search endpoint did not crash
assert response.status_code == 200
# fallback on title_search
assert mock_title_search.call_count == 1
assert mock_title_search.call_args[0][0].GET.get("q") == q
assert mock_title_search.call_args[0][0].GET.get("path") == parent.path
assert response.json() == mocked_response
@responses.activate
def test_api_documents_search_invalid_params(indexer_settings):
"""Validate the format of documents as returned by the search view."""
indexer_settings.SEARCH_INDEXER_QUERY_URL = "http://find/api/v1.0/search"
indexer_settings.SEARCH_URL = "http://find/api/v1.0/search"
assert get_document_indexer() is not None
user = factories.UserFactory()
client = APIClient()
client.force_login(user)
@@ -125,49 +182,28 @@ def test_api_documents_search_invalid_params(indexer_settings):
assert response.status_code == 400
assert response.json() == {"q": ["This field is required."]}
response = client.get("/api/v1.0/documents/search/", data={"q": " "})
assert response.status_code == 400
assert response.json() == {"q": ["This field may not be blank."]}
response = client.get(
"/api/v1.0/documents/search/", data={"q": "any", "page": "NaN"}
)
assert response.status_code == 400
assert response.json() == {"page": ["A valid integer is required."]}
@responses.activate
def test_api_documents_search_format(indexer_settings):
def test_api_documents_search_success(indexer_settings):
"""Validate the format of documents as returned by the search view."""
indexer_settings.SEARCH_INDEXER_QUERY_URL = "http://find/api/v1.0/search"
indexer_settings.SEARCH_URL = "http://find/api/v1.0/search"
assert get_document_indexer() is not None
user = factories.UserFactory()
client = APIClient()
client.force_login(user)
user_a, user_b, user_c = factories.UserFactory.create_batch(3)
document = factories.DocumentFactory(
title="alpha",
users=(user_a, user_c),
link_traces=(user, user_b),
)
access = factories.UserDocumentAccessFactory(document=document, user=user)
document = {"id": "doc-123", "title": "alpha", "path": "path/to/alpha.pdf"}
# Find response
responses.add(
responses.POST,
"http://find/api/v1.0/search",
json=[
{"_id": str(document.pk)},
{
"_id": str(document["id"]),
"_source": {"title": document["title"], "path": document["path"]},
},
],
status=200,
)
response = client.get("/api/v1.0/documents/search/", data={"q": "alpha"})
response = APIClient().get("/api/v1.0/documents/search/", data={"q": "alpha"})
assert response.status_code == 200
content = response.json()
@@ -177,249 +213,6 @@ def test_api_documents_search_format(indexer_settings):
"next": None,
"previous": None,
}
assert len(results) == 1
assert results[0] == {
"id": str(document.id),
"abilities": document.get_abilities(user),
"ancestors_link_reach": None,
"ancestors_link_role": None,
"computed_link_reach": document.computed_link_reach,
"computed_link_role": document.computed_link_role,
"created_at": document.created_at.isoformat().replace("+00:00", "Z"),
"creator": str(document.creator.id),
"depth": 1,
"excerpt": document.excerpt,
"link_reach": document.link_reach,
"link_role": document.link_role,
"nb_accesses_ancestors": 3,
"nb_accesses_direct": 3,
"numchild": 0,
"path": document.path,
"title": document.title,
"updated_at": document.updated_at.isoformat().replace("+00:00", "Z"),
"deleted_at": None,
"user_role": access.role,
}
@responses.activate
@pytest.mark.parametrize(
"pagination, status, expected",
(
(
{"page": 1, "page_size": 10},
200,
{
"count": 10,
"previous": None,
"next": None,
"range": (0, None),
},
),
(
{},
200,
{
"count": 10,
"previous": None,
"next": None,
"range": (0, None),
"api_page_size": 21, # default page_size is 20
},
),
(
{"page": 2, "page_size": 10},
404,
{},
),
(
{"page": 1, "page_size": 5},
200,
{
"count": 10,
"previous": None,
"next": {"page": 2, "page_size": 5},
"range": (0, 5),
},
),
(
{"page": 2, "page_size": 5},
200,
{
"count": 10,
"previous": {"page_size": 5},
"next": None,
"range": (5, None),
},
),
({"page": 3, "page_size": 5}, 404, {}),
),
)
def test_api_documents_search_pagination(
indexer_settings, pagination, status, expected
):
"""Documents should be ordered by descending "score" by default"""
indexer_settings.SEARCH_INDEXER_QUERY_URL = "http://find/api/v1.0/search"
assert get_document_indexer() is not None
user = factories.UserFactory()
client = APIClient()
client.force_login(user)
docs = factories.DocumentFactory.create_batch(10, title="alpha", users=[user])
docs_by_uuid = {str(doc.pk): doc for doc in docs}
api_results = [{"_id": id} for id in docs_by_uuid.keys()]
# reorder randomly to simulate score ordering
random.shuffle(api_results)
# Find response
# pylint: disable-next=assignment-from-none
api_search = responses.add(
responses.POST,
"http://find/api/v1.0/search",
json=api_results,
status=200,
)
response = client.get(
"/api/v1.0/documents/search/",
data={
"q": "alpha",
**pagination,
},
)
assert response.status_code == status
if response.status_code < 300:
previous_url = (
build_search_url(q="alpha", **expected["previous"])
if expected["previous"]
else None
)
next_url = (
build_search_url(q="alpha", **expected["next"])
if expected["next"]
else None
)
start, end = expected["range"]
content = response.json()
assert content["count"] == expected["count"]
assert content["previous"] == previous_url
assert content["next"] == next_url
results = content.pop("results")
# The find api results ordering by score is kept
assert [r["id"] for r in results] == [r["_id"] for r in api_results[start:end]]
# Check the query parameters.
assert api_search.call_count == 1
assert api_search.calls[0].response.status_code == 200
assert json_loads(api_search.calls[0].request.body) == {
"q": "alpha",
"visited": [],
"services": ["docs"],
"nb_results": 50,
"order_by": "updated_at",
"order_direction": "desc",
}
@responses.activate
@pytest.mark.parametrize(
"pagination, status, expected",
(
(
{"page": 1, "page_size": 10},
200,
{"count": 10, "previous": None, "next": None, "range": (0, None)},
),
(
{},
200,
{"count": 10, "previous": None, "next": None, "range": (0, None)},
),
(
{"page": 2, "page_size": 10},
404,
{},
),
(
{"page": 1, "page_size": 5},
200,
{
"count": 10,
"previous": None,
"next": {"page": 2, "page_size": 5},
"range": (0, 5),
},
),
(
{"page": 2, "page_size": 5},
200,
{
"count": 10,
"previous": {"page_size": 5},
"next": None,
"range": (5, None),
},
),
({"page": 3, "page_size": 5}, 404, {}),
),
)
def test_api_documents_search_pagination_endpoint_is_none(
indexer_settings, pagination, status, expected
):
"""Documents should be ordered by descending "-updated_at" by default"""
indexer_settings.SEARCH_INDEXER_QUERY_URL = None
assert get_document_indexer() is None
user = factories.UserFactory()
client = APIClient()
client.force_login(user)
factories.DocumentFactory.create_batch(10, title="alpha", users=[user])
response = client.get(
"/api/v1.0/documents/search/",
data={
"q": "alpha",
**pagination,
},
)
assert response.status_code == status
if response.status_code < 300:
previous_url = (
build_search_url(q="alpha", **expected["previous"])
if expected["previous"]
else None
)
next_url = (
build_search_url(q="alpha", **expected["next"])
if expected["next"]
else None
)
queryset = models.Document.objects.order_by("-updated_at")
start, end = expected["range"]
expected_results = [str(d.pk) for d in queryset[start:end]]
content = response.json()
assert content["count"] == expected["count"]
assert content["previous"] == previous_url
assert content["next"] == next_url
results = content.pop("results")
assert [r["id"] for r in results] == expected_results
assert results == [
{"id": document["id"], "title": document["title"], "path": document["path"]}
]
@@ -0,0 +1,956 @@
"""
Tests for search API endpoint in impress's core app when indexer is not
available and a path param is given.
"""
import random
from django.contrib.auth.models import AnonymousUser
import pytest
from rest_framework.test import APIClient
from core import factories
from core.api.filters import remove_accents
pytestmark = pytest.mark.django_db
@pytest.fixture(autouse=True)
def disable_indexer(indexer_settings):
"""Disable search indexer for all tests in this file."""
indexer_settings.SEARCH_INDEXER_CLASS = None
def test_api_documents_search_descendants_list_anonymous_public_standalone():
"""Anonymous users should be allowed to retrieve the descendants of a public document."""
document = factories.DocumentFactory(link_reach="public", title="doc parent")
child1, child2 = factories.DocumentFactory.create_batch(
2, parent=document, title="doc child"
)
grand_child = factories.DocumentFactory(parent=child1, title="doc grand child")
factories.UserDocumentAccessFactory(document=child1)
response = APIClient().get(
"/api/v1.0/documents/search/", data={"q": "doc", "path": document.path}
)
assert response.status_code == 200
assert response.json() == {
"count": 4,
"next": None,
"previous": None,
"results": [
{
# the search should include the parent document itself
"abilities": document.get_abilities(AnonymousUser()),
"ancestors_link_role": None,
"ancestors_link_reach": None,
"computed_link_reach": document.computed_link_reach,
"computed_link_role": document.computed_link_role,
"created_at": document.created_at.isoformat().replace("+00:00", "Z"),
"creator": str(document.creator.id),
"deleted_at": None,
"depth": 1,
"excerpt": document.excerpt,
"id": str(document.id),
"is_favorite": False,
"link_reach": document.link_reach,
"link_role": document.link_role,
"numchild": 2,
"nb_accesses_ancestors": 0,
"nb_accesses_direct": 0,
"path": document.path,
"title": document.title,
"updated_at": document.updated_at.isoformat().replace("+00:00", "Z"),
"user_role": None,
},
{
"abilities": child1.get_abilities(AnonymousUser()),
"ancestors_link_reach": document.link_reach,
"ancestors_link_role": document.link_role,
"computed_link_reach": child1.computed_link_reach,
"computed_link_role": child1.computed_link_role,
"created_at": child1.created_at.isoformat().replace("+00:00", "Z"),
"creator": str(child1.creator.id),
"deleted_at": None,
"depth": 2,
"excerpt": child1.excerpt,
"id": str(child1.id),
"is_favorite": False,
"link_reach": child1.link_reach,
"link_role": child1.link_role,
"numchild": 1,
"nb_accesses_ancestors": 1,
"nb_accesses_direct": 1,
"path": child1.path,
"title": child1.title,
"updated_at": child1.updated_at.isoformat().replace("+00:00", "Z"),
"user_role": None,
},
{
"abilities": grand_child.get_abilities(AnonymousUser()),
"ancestors_link_reach": document.link_reach,
"ancestors_link_role": document.link_role
if (child1.link_reach == "public" and child1.link_role == "editor")
else document.link_role,
"computed_link_reach": "public",
"computed_link_role": grand_child.computed_link_role,
"created_at": grand_child.created_at.isoformat().replace("+00:00", "Z"),
"creator": str(grand_child.creator.id),
"deleted_at": None,
"depth": 3,
"excerpt": grand_child.excerpt,
"id": str(grand_child.id),
"is_favorite": False,
"link_reach": grand_child.link_reach,
"link_role": grand_child.link_role,
"numchild": 0,
"nb_accesses_ancestors": 1,
"nb_accesses_direct": 0,
"path": grand_child.path,
"title": grand_child.title,
"updated_at": grand_child.updated_at.isoformat().replace("+00:00", "Z"),
"user_role": None,
},
{
"abilities": child2.get_abilities(AnonymousUser()),
"ancestors_link_reach": document.link_reach,
"ancestors_link_role": document.link_role,
"computed_link_reach": "public",
"computed_link_role": child2.computed_link_role,
"created_at": child2.created_at.isoformat().replace("+00:00", "Z"),
"creator": str(child2.creator.id),
"deleted_at": None,
"depth": 2,
"excerpt": child2.excerpt,
"id": str(child2.id),
"is_favorite": False,
"link_reach": child2.link_reach,
"link_role": child2.link_role,
"numchild": 0,
"nb_accesses_ancestors": 0,
"nb_accesses_direct": 0,
"path": child2.path,
"title": child2.title,
"updated_at": child2.updated_at.isoformat().replace("+00:00", "Z"),
"user_role": None,
},
],
}
def test_api_documents_search_descendants_list_anonymous_public_parent():
"""
Anonymous users should be allowed to retrieve the descendants of a document who
has a public ancestor.
"""
grand_parent = factories.DocumentFactory(
link_reach="public", title="grand parent doc"
)
parent = factories.DocumentFactory(
parent=grand_parent,
link_reach=random.choice(["authenticated", "restricted"]),
title="parent doc",
)
document = factories.DocumentFactory(
link_reach=random.choice(["authenticated", "restricted"]),
parent=parent,
title="document",
)
child1, child2 = factories.DocumentFactory.create_batch(
2, parent=document, title="child doc"
)
grand_child = factories.DocumentFactory(parent=child1, title="grand child doc")
factories.UserDocumentAccessFactory(document=child1)
response = APIClient().get(
"/api/v1.0/documents/search/", data={"q": "doc", "path": document.path}
)
assert response.status_code == 200
assert response.json() == {
"count": 4,
"next": None,
"previous": None,
"results": [
{
# the search should include the parent document itself
"abilities": document.get_abilities(AnonymousUser()),
"ancestors_link_reach": "public",
"ancestors_link_role": grand_parent.link_role,
"computed_link_reach": document.computed_link_reach,
"computed_link_role": document.computed_link_role,
"created_at": document.created_at.isoformat().replace("+00:00", "Z"),
"creator": str(document.creator.id),
"deleted_at": None,
"depth": 3,
"excerpt": document.excerpt,
"id": str(document.id),
"is_favorite": False,
"link_reach": document.link_reach,
"link_role": document.link_role,
"numchild": 2,
"nb_accesses_ancestors": 0,
"nb_accesses_direct": 0,
"path": document.path,
"title": document.title,
"updated_at": document.updated_at.isoformat().replace("+00:00", "Z"),
"user_role": None,
},
{
"abilities": child1.get_abilities(AnonymousUser()),
"ancestors_link_reach": "public",
"ancestors_link_role": grand_parent.link_role,
"computed_link_reach": child1.computed_link_reach,
"computed_link_role": child1.computed_link_role,
"created_at": child1.created_at.isoformat().replace("+00:00", "Z"),
"creator": str(child1.creator.id),
"deleted_at": None,
"depth": 4,
"excerpt": child1.excerpt,
"id": str(child1.id),
"is_favorite": False,
"link_reach": child1.link_reach,
"link_role": child1.link_role,
"numchild": 1,
"nb_accesses_ancestors": 1,
"nb_accesses_direct": 1,
"path": child1.path,
"title": child1.title,
"updated_at": child1.updated_at.isoformat().replace("+00:00", "Z"),
"user_role": None,
},
{
"abilities": grand_child.get_abilities(AnonymousUser()),
"ancestors_link_reach": "public",
"ancestors_link_role": grand_child.ancestors_link_role,
"computed_link_reach": "public",
"computed_link_role": grand_child.computed_link_role,
"created_at": grand_child.created_at.isoformat().replace("+00:00", "Z"),
"creator": str(grand_child.creator.id),
"deleted_at": None,
"depth": 5,
"excerpt": grand_child.excerpt,
"id": str(grand_child.id),
"is_favorite": False,
"link_reach": grand_child.link_reach,
"link_role": grand_child.link_role,
"numchild": 0,
"nb_accesses_ancestors": 1,
"nb_accesses_direct": 0,
"path": grand_child.path,
"title": grand_child.title,
"updated_at": grand_child.updated_at.isoformat().replace("+00:00", "Z"),
"user_role": None,
},
{
"abilities": child2.get_abilities(AnonymousUser()),
"ancestors_link_reach": "public",
"ancestors_link_role": grand_parent.link_role,
"computed_link_reach": "public",
"computed_link_role": child2.computed_link_role,
"created_at": child2.created_at.isoformat().replace("+00:00", "Z"),
"creator": str(child2.creator.id),
"deleted_at": None,
"depth": 4,
"excerpt": child2.excerpt,
"id": str(child2.id),
"is_favorite": False,
"link_reach": child2.link_reach,
"link_role": child2.link_role,
"numchild": 0,
"nb_accesses_ancestors": 0,
"nb_accesses_direct": 0,
"path": child2.path,
"title": child2.title,
"updated_at": child2.updated_at.isoformat().replace("+00:00", "Z"),
"user_role": None,
},
],
}
@pytest.mark.parametrize("reach", ["restricted", "authenticated"])
def test_api_documents_search_descendants_list_anonymous_restricted_or_authenticated(
reach,
):
"""
Anonymous users should not be able to retrieve descendants of a document that is not public.
"""
document = factories.DocumentFactory(title="parent", link_reach=reach)
child = factories.DocumentFactory(title="child", parent=document)
_grand_child = factories.DocumentFactory(title="grand child", parent=child)
response = APIClient().get(
"/api/v1.0/documents/search/", data={"q": "child", "path": document.path}
)
assert response.status_code == 403
assert response.json() == {
"detail": "You do not have permission to search within this document."
}
@pytest.mark.parametrize("reach", ["public", "authenticated"])
def test_api_documents_search_descendants_list_authenticated_unrelated_public_or_authenticated(
reach,
):
"""
Authenticated users should be able to retrieve the descendants of a public/authenticated
document to which they are not related.
"""
user = factories.UserFactory()
client = APIClient()
client.force_login(user)
document = factories.DocumentFactory(link_reach=reach, title="parent")
child1, child2 = factories.DocumentFactory.create_batch(
2, parent=document, link_reach="restricted", title="child"
)
grand_child = factories.DocumentFactory(parent=child1, title="grand child")
factories.UserDocumentAccessFactory(document=child1)
response = client.get(
"/api/v1.0/documents/search/", data={"q": "child", "path": document.path}
)
assert response.status_code == 200
assert response.json() == {
"count": 3,
"next": None,
"previous": None,
"results": [
{
"abilities": child1.get_abilities(user),
"ancestors_link_reach": reach,
"ancestors_link_role": document.link_role,
"computed_link_reach": child1.computed_link_reach,
"computed_link_role": child1.computed_link_role,
"created_at": child1.created_at.isoformat().replace("+00:00", "Z"),
"creator": str(child1.creator.id),
"deleted_at": None,
"depth": 2,
"excerpt": child1.excerpt,
"id": str(child1.id),
"is_favorite": False,
"link_reach": child1.link_reach,
"link_role": child1.link_role,
"numchild": 1,
"nb_accesses_ancestors": 1,
"nb_accesses_direct": 1,
"path": child1.path,
"title": child1.title,
"updated_at": child1.updated_at.isoformat().replace("+00:00", "Z"),
"user_role": None,
},
{
"abilities": grand_child.get_abilities(user),
"ancestors_link_reach": reach,
"ancestors_link_role": document.link_role,
"computed_link_reach": grand_child.computed_link_reach,
"computed_link_role": grand_child.computed_link_role,
"created_at": grand_child.created_at.isoformat().replace("+00:00", "Z"),
"creator": str(grand_child.creator.id),
"deleted_at": None,
"depth": 3,
"excerpt": grand_child.excerpt,
"id": str(grand_child.id),
"is_favorite": False,
"link_reach": grand_child.link_reach,
"link_role": grand_child.link_role,
"numchild": 0,
"nb_accesses_ancestors": 1,
"nb_accesses_direct": 0,
"path": grand_child.path,
"title": grand_child.title,
"updated_at": grand_child.updated_at.isoformat().replace("+00:00", "Z"),
"user_role": None,
},
{
"abilities": child2.get_abilities(user),
"ancestors_link_reach": reach,
"ancestors_link_role": document.link_role,
"computed_link_reach": child2.computed_link_reach,
"computed_link_role": child2.computed_link_role,
"created_at": child2.created_at.isoformat().replace("+00:00", "Z"),
"creator": str(child2.creator.id),
"deleted_at": None,
"depth": 2,
"excerpt": child2.excerpt,
"id": str(child2.id),
"is_favorite": False,
"link_reach": child2.link_reach,
"link_role": child2.link_role,
"numchild": 0,
"nb_accesses_ancestors": 0,
"nb_accesses_direct": 0,
"path": child2.path,
"title": child2.title,
"updated_at": child2.updated_at.isoformat().replace("+00:00", "Z"),
"user_role": None,
},
],
}
@pytest.mark.parametrize("reach", ["public", "authenticated"])
def test_api_documents_search_descendants_list_authenticated_public_or_authenticated_parent(
reach,
):
"""
Authenticated users should be allowed to retrieve the descendants of a document who
has a public or authenticated ancestor.
"""
user = factories.UserFactory()
client = APIClient()
client.force_login(user)
grand_parent = factories.DocumentFactory(link_reach=reach, title="grand parent")
parent = factories.DocumentFactory(
parent=grand_parent, link_reach="restricted", title="parent"
)
document = factories.DocumentFactory(
link_reach="restricted", parent=parent, title="document"
)
child1, child2 = factories.DocumentFactory.create_batch(
2, parent=document, link_reach="restricted", title="child"
)
grand_child = factories.DocumentFactory(parent=child1, title="grand child")
factories.UserDocumentAccessFactory(document=child1)
response = client.get(
"/api/v1.0/documents/search/", data={"q": "child", "path": document.path}
)
assert response.status_code == 200
assert response.json() == {
"count": 3,
"next": None,
"previous": None,
"results": [
{
"abilities": child1.get_abilities(user),
"ancestors_link_reach": reach,
"ancestors_link_role": grand_parent.link_role,
"computed_link_reach": child1.computed_link_reach,
"computed_link_role": child1.computed_link_role,
"created_at": child1.created_at.isoformat().replace("+00:00", "Z"),
"creator": str(child1.creator.id),
"deleted_at": None,
"depth": 4,
"excerpt": child1.excerpt,
"id": str(child1.id),
"is_favorite": False,
"link_reach": child1.link_reach,
"link_role": child1.link_role,
"numchild": 1,
"nb_accesses_ancestors": 1,
"nb_accesses_direct": 1,
"path": child1.path,
"title": child1.title,
"updated_at": child1.updated_at.isoformat().replace("+00:00", "Z"),
"user_role": None,
},
{
"abilities": grand_child.get_abilities(user),
"ancestors_link_reach": reach,
"ancestors_link_role": grand_parent.link_role,
"computed_link_reach": grand_child.computed_link_reach,
"computed_link_role": grand_child.computed_link_role,
"created_at": grand_child.created_at.isoformat().replace("+00:00", "Z"),
"creator": str(grand_child.creator.id),
"deleted_at": None,
"depth": 5,
"excerpt": grand_child.excerpt,
"id": str(grand_child.id),
"is_favorite": False,
"link_reach": grand_child.link_reach,
"link_role": grand_child.link_role,
"numchild": 0,
"nb_accesses_ancestors": 1,
"nb_accesses_direct": 0,
"path": grand_child.path,
"title": grand_child.title,
"updated_at": grand_child.updated_at.isoformat().replace("+00:00", "Z"),
"user_role": None,
},
{
"abilities": child2.get_abilities(user),
"ancestors_link_reach": reach,
"ancestors_link_role": grand_parent.link_role,
"computed_link_reach": child2.computed_link_reach,
"computed_link_role": child2.computed_link_role,
"created_at": child2.created_at.isoformat().replace("+00:00", "Z"),
"creator": str(child2.creator.id),
"deleted_at": None,
"depth": 4,
"excerpt": child2.excerpt,
"id": str(child2.id),
"is_favorite": False,
"link_reach": child2.link_reach,
"link_role": child2.link_role,
"numchild": 0,
"nb_accesses_ancestors": 0,
"nb_accesses_direct": 0,
"path": child2.path,
"title": child2.title,
"updated_at": child2.updated_at.isoformat().replace("+00:00", "Z"),
"user_role": None,
},
],
}
def test_api_documents_search_descendants_list_authenticated_unrelated_restricted():
"""
Authenticated users should not be allowed to retrieve the descendants of a document that is
restricted and to which they are not related.
"""
user = factories.UserFactory(with_owned_document=True)
client = APIClient()
client.force_login(user)
document = factories.DocumentFactory(link_reach="restricted", title="parent")
child1, _child2 = factories.DocumentFactory.create_batch(
2, parent=document, title="child"
)
_grand_child = factories.DocumentFactory(parent=child1, title="grand child")
factories.UserDocumentAccessFactory(document=child1)
response = client.get(
"/api/v1.0/documents/search/", data={"q": "child", "path": document.path}
)
assert response.status_code == 403
assert response.json() == {
"detail": "You do not have permission to search within this document."
}
def test_api_documents_search_descendants_list_authenticated_related_direct():
"""
Authenticated users should be allowed to retrieve the descendants of a document
to which they are directly related whatever the role.
"""
user = factories.UserFactory()
client = APIClient()
client.force_login(user)
document = factories.DocumentFactory(title="parent")
access = factories.UserDocumentAccessFactory(document=document, user=user)
factories.UserDocumentAccessFactory(document=document)
child1, child2 = factories.DocumentFactory.create_batch(
2, parent=document, title="child"
)
factories.UserDocumentAccessFactory(document=child1)
grand_child = factories.DocumentFactory(parent=child1, title="grand child")
response = client.get(
"/api/v1.0/documents/search/", data={"q": "child", "path": document.path}
)
assert response.status_code == 200
assert response.json() == {
"count": 3,
"next": None,
"previous": None,
"results": [
{
"abilities": child1.get_abilities(user),
"ancestors_link_reach": child1.ancestors_link_reach,
"ancestors_link_role": child1.ancestors_link_role,
"computed_link_reach": child1.computed_link_reach,
"computed_link_role": child1.computed_link_role,
"created_at": child1.created_at.isoformat().replace("+00:00", "Z"),
"creator": str(child1.creator.id),
"deleted_at": None,
"depth": 2,
"excerpt": child1.excerpt,
"id": str(child1.id),
"is_favorite": False,
"link_reach": child1.link_reach,
"link_role": child1.link_role,
"numchild": 1,
"nb_accesses_ancestors": 3,
"nb_accesses_direct": 1,
"path": child1.path,
"title": child1.title,
"updated_at": child1.updated_at.isoformat().replace("+00:00", "Z"),
"user_role": access.role,
},
{
"abilities": grand_child.get_abilities(user),
"ancestors_link_reach": grand_child.ancestors_link_reach,
"ancestors_link_role": grand_child.ancestors_link_role,
"computed_link_reach": grand_child.computed_link_reach,
"computed_link_role": grand_child.computed_link_role,
"created_at": grand_child.created_at.isoformat().replace("+00:00", "Z"),
"creator": str(grand_child.creator.id),
"deleted_at": None,
"depth": 3,
"excerpt": grand_child.excerpt,
"id": str(grand_child.id),
"is_favorite": False,
"link_reach": grand_child.link_reach,
"link_role": grand_child.link_role,
"numchild": 0,
"nb_accesses_ancestors": 3,
"nb_accesses_direct": 0,
"path": grand_child.path,
"title": grand_child.title,
"updated_at": grand_child.updated_at.isoformat().replace("+00:00", "Z"),
"user_role": access.role,
},
{
"abilities": child2.get_abilities(user),
"ancestors_link_reach": child2.ancestors_link_reach,
"ancestors_link_role": child2.ancestors_link_role,
"computed_link_reach": child2.computed_link_reach,
"computed_link_role": child2.computed_link_role,
"created_at": child2.created_at.isoformat().replace("+00:00", "Z"),
"creator": str(child2.creator.id),
"deleted_at": None,
"depth": 2,
"excerpt": child2.excerpt,
"id": str(child2.id),
"is_favorite": False,
"link_reach": child2.link_reach,
"link_role": child2.link_role,
"numchild": 0,
"nb_accesses_ancestors": 2,
"nb_accesses_direct": 0,
"path": child2.path,
"title": child2.title,
"updated_at": child2.updated_at.isoformat().replace("+00:00", "Z"),
"user_role": access.role,
},
],
}
def test_api_documents_search_descendants_list_authenticated_related_parent():
"""
Authenticated users should be allowed to retrieve the descendants of a document if they
are related to one of its ancestors whatever the role.
"""
user = factories.UserFactory()
client = APIClient()
client.force_login(user)
grand_parent = factories.DocumentFactory(link_reach="restricted", title="parent")
grand_parent_access = factories.UserDocumentAccessFactory(
document=grand_parent, user=user
)
parent = factories.DocumentFactory(
parent=grand_parent, link_reach="restricted", title="parent"
)
document = factories.DocumentFactory(
parent=parent, link_reach="restricted", title="document"
)
child1, child2 = factories.DocumentFactory.create_batch(
2, parent=document, title="child"
)
factories.UserDocumentAccessFactory(document=child1)
grand_child = factories.DocumentFactory(parent=child1, title="grand child")
response = client.get(
"/api/v1.0/documents/search/", data={"q": "child", "path": document.path}
)
assert response.status_code == 200
assert response.json() == {
"count": 3,
"next": None,
"previous": None,
"results": [
{
"abilities": child1.get_abilities(user),
"ancestors_link_reach": child1.ancestors_link_reach,
"ancestors_link_role": child1.ancestors_link_role,
"computed_link_reach": child1.computed_link_reach,
"computed_link_role": child1.computed_link_role,
"created_at": child1.created_at.isoformat().replace("+00:00", "Z"),
"creator": str(child1.creator.id),
"deleted_at": None,
"depth": 4,
"excerpt": child1.excerpt,
"id": str(child1.id),
"is_favorite": False,
"link_reach": child1.link_reach,
"link_role": child1.link_role,
"numchild": 1,
"nb_accesses_ancestors": 2,
"nb_accesses_direct": 1,
"path": child1.path,
"title": child1.title,
"updated_at": child1.updated_at.isoformat().replace("+00:00", "Z"),
"user_role": grand_parent_access.role,
},
{
"abilities": grand_child.get_abilities(user),
"ancestors_link_reach": grand_child.ancestors_link_reach,
"ancestors_link_role": grand_child.ancestors_link_role,
"computed_link_reach": grand_child.computed_link_reach,
"computed_link_role": grand_child.computed_link_role,
"created_at": grand_child.created_at.isoformat().replace("+00:00", "Z"),
"creator": str(grand_child.creator.id),
"deleted_at": None,
"depth": 5,
"excerpt": grand_child.excerpt,
"id": str(grand_child.id),
"is_favorite": False,
"link_reach": grand_child.link_reach,
"link_role": grand_child.link_role,
"numchild": 0,
"nb_accesses_ancestors": 2,
"nb_accesses_direct": 0,
"path": grand_child.path,
"title": grand_child.title,
"updated_at": grand_child.updated_at.isoformat().replace("+00:00", "Z"),
"user_role": grand_parent_access.role,
},
{
"abilities": child2.get_abilities(user),
"ancestors_link_reach": child2.ancestors_link_reach,
"ancestors_link_role": child2.ancestors_link_role,
"computed_link_reach": child2.computed_link_reach,
"computed_link_role": child2.computed_link_role,
"created_at": child2.created_at.isoformat().replace("+00:00", "Z"),
"creator": str(child2.creator.id),
"deleted_at": None,
"depth": 4,
"excerpt": child2.excerpt,
"id": str(child2.id),
"is_favorite": False,
"link_reach": child2.link_reach,
"link_role": child2.link_role,
"numchild": 0,
"nb_accesses_ancestors": 1,
"nb_accesses_direct": 0,
"path": child2.path,
"title": child2.title,
"updated_at": child2.updated_at.isoformat().replace("+00:00", "Z"),
"user_role": grand_parent_access.role,
},
],
}
def test_api_documents_search_descendants_list_authenticated_related_child():
"""
Authenticated users should not be allowed to retrieve all the descendants of a document
as a result of being related to one of its children.
"""
user = factories.UserFactory()
client = APIClient()
client.force_login(user)
document = factories.DocumentFactory(link_reach="restricted")
child1, _child2 = factories.DocumentFactory.create_batch(2, parent=document)
_grand_child = factories.DocumentFactory(parent=child1)
factories.UserDocumentAccessFactory(document=child1, user=user)
factories.UserDocumentAccessFactory(document=document)
response = client.get(
"/api/v1.0/documents/search/", data={"q": "doc", "path": document.path}
)
assert response.status_code == 403
assert response.json() == {
"detail": "You do not have permission to search within this document."
}
def test_api_documents_search_descendants_list_authenticated_related_team_none(
mock_user_teams,
):
"""
Authenticated users should not be able to retrieve the descendants of a restricted document
related to teams in which the user is not.
"""
mock_user_teams.return_value = []
user = factories.UserFactory(with_owned_document=True)
client = APIClient()
client.force_login(user)
document = factories.DocumentFactory(link_reach="restricted", title="document")
factories.DocumentFactory.create_batch(2, parent=document, title="child")
factories.TeamDocumentAccessFactory(document=document, team="myteam")
response = client.get(
"/api/v1.0/documents/search/", data={"q": "doc", "path": document.path}
)
assert response.status_code == 403
assert response.json() == {
"detail": "You do not have permission to search within this document."
}
def test_api_documents_search_descendants_list_authenticated_related_team_members(
mock_user_teams,
):
"""
Authenticated users should be allowed to retrieve the descendants of a document to which they
are related via a team whatever the role.
"""
mock_user_teams.return_value = ["myteam"]
user = factories.UserFactory()
client = APIClient()
client.force_login(user)
document = factories.DocumentFactory(link_reach="restricted", title="parent")
child1, child2 = factories.DocumentFactory.create_batch(
2, parent=document, title="child"
)
grand_child = factories.DocumentFactory(parent=child1, title="grand child")
access = factories.TeamDocumentAccessFactory(document=document, team="myteam")
response = client.get(
"/api/v1.0/documents/search/", data={"q": "child", "path": document.path}
)
# pylint: disable=R0801
assert response.status_code == 200
assert response.json() == {
"count": 3,
"next": None,
"previous": None,
"results": [
{
"abilities": child1.get_abilities(user),
"ancestors_link_reach": child1.ancestors_link_reach,
"ancestors_link_role": child1.ancestors_link_role,
"computed_link_reach": child1.computed_link_reach,
"computed_link_role": child1.computed_link_role,
"created_at": child1.created_at.isoformat().replace("+00:00", "Z"),
"creator": str(child1.creator.id),
"deleted_at": None,
"depth": 2,
"excerpt": child1.excerpt,
"id": str(child1.id),
"is_favorite": False,
"link_reach": child1.link_reach,
"link_role": child1.link_role,
"numchild": 1,
"nb_accesses_ancestors": 1,
"nb_accesses_direct": 0,
"path": child1.path,
"title": child1.title,
"updated_at": child1.updated_at.isoformat().replace("+00:00", "Z"),
"user_role": access.role,
},
{
"abilities": grand_child.get_abilities(user),
"ancestors_link_reach": grand_child.ancestors_link_reach,
"ancestors_link_role": grand_child.ancestors_link_role,
"computed_link_reach": grand_child.computed_link_reach,
"computed_link_role": grand_child.computed_link_role,
"created_at": grand_child.created_at.isoformat().replace("+00:00", "Z"),
"creator": str(grand_child.creator.id),
"deleted_at": None,
"depth": 3,
"excerpt": grand_child.excerpt,
"id": str(grand_child.id),
"is_favorite": False,
"link_reach": grand_child.link_reach,
"link_role": grand_child.link_role,
"numchild": 0,
"nb_accesses_ancestors": 1,
"nb_accesses_direct": 0,
"path": grand_child.path,
"title": grand_child.title,
"updated_at": grand_child.updated_at.isoformat().replace("+00:00", "Z"),
"user_role": access.role,
},
{
"abilities": child2.get_abilities(user),
"ancestors_link_reach": child2.ancestors_link_reach,
"ancestors_link_role": child2.ancestors_link_role,
"computed_link_reach": child2.computed_link_reach,
"computed_link_role": child2.computed_link_role,
"created_at": child2.created_at.isoformat().replace("+00:00", "Z"),
"creator": str(child2.creator.id),
"deleted_at": None,
"depth": 2,
"excerpt": child2.excerpt,
"id": str(child2.id),
"is_favorite": False,
"link_reach": child2.link_reach,
"link_role": child2.link_role,
"numchild": 0,
"nb_accesses_ancestors": 1,
"nb_accesses_direct": 0,
"path": child2.path,
"title": child2.title,
"updated_at": child2.updated_at.isoformat().replace("+00:00", "Z"),
"user_role": access.role,
},
],
}
@pytest.mark.parametrize(
"query,nb_results",
[
("", 7), # Empty string
("Project Alpha", 1), # Exact match
("project", 2), # Partial match (case-insensitive)
("Guide", 2), # Word match within a title
("Special", 0), # No match (nonexistent keyword)
("2024", 2), # Match by numeric keyword
("velo", 1), # Accent-insensitive match (velo vs vélo)
("bêta", 1), # Accent-insensitive match (bêta vs beta)
],
)
def test_api_documents_search_descendants_search_on_title(query, nb_results):
"""Authenticated users should be able to search documents by their unaccented title."""
user = factories.UserFactory()
client = APIClient()
client.force_login(user)
parent = factories.DocumentFactory(users=[user])
# Create documents with predefined titles
titles = [
"Project Alpha Documentation",
"Project Beta Overview",
"User Guide",
"Financial Report 2024",
"Annual Review 2024",
"Guide du vélo urbain", # <-- Title with accent for accent-insensitive test
]
for title in titles:
factories.DocumentFactory(title=title, parent=parent)
# Perform the search query
response = client.get(
"/api/v1.0/documents/search/", data={"q": query, "path": parent.path}
)
assert response.status_code == 200
results = response.json()["results"]
assert len(results) == nb_results
# Ensure all results contain the query in their title
for result in results:
assert (
remove_accents(query).lower().strip()
in remove_accents(result["title"]).lower()
)
@@ -101,6 +101,7 @@ def test_api_documents_trashbin_format():
"partial_update": False,
"restore": True,
"retrieve": True,
"search": False,
"tree": True,
"update": False,
"versions_destroy": False,
@@ -189,6 +189,7 @@ def test_models_documents_get_abilities_forbidden(
"versions_destroy": False,
"versions_list": False,
"versions_retrieve": False,
"search": False,
}
nb_queries = 1 if is_authenticated else 0
with django_assert_num_queries(nb_queries):
@@ -255,6 +256,7 @@ def test_models_documents_get_abilities_reader(
"versions_destroy": False,
"versions_list": False,
"versions_retrieve": False,
"search": True,
}
nb_queries = 1 if is_authenticated else 0
with django_assert_num_queries(nb_queries):
@@ -326,6 +328,7 @@ def test_models_documents_get_abilities_commenter(
"versions_destroy": False,
"versions_list": False,
"versions_retrieve": False,
"search": True,
}
nb_queries = 1 if is_authenticated else 0
with django_assert_num_queries(nb_queries):
@@ -394,6 +397,7 @@ def test_models_documents_get_abilities_editor(
"versions_destroy": False,
"versions_list": False,
"versions_retrieve": False,
"search": True,
}
nb_queries = 1 if is_authenticated else 0
with django_assert_num_queries(nb_queries):
@@ -451,6 +455,7 @@ def test_models_documents_get_abilities_owner(django_assert_num_queries):
"versions_destroy": True,
"versions_list": True,
"versions_retrieve": True,
"search": True,
}
with django_assert_num_queries(1):
assert document.get_abilities(user) == expected_abilities
@@ -494,6 +499,7 @@ def test_models_documents_get_abilities_owner(django_assert_num_queries):
"versions_destroy": False,
"versions_list": False,
"versions_retrieve": False,
"search": False,
}
@@ -541,6 +547,7 @@ def test_models_documents_get_abilities_administrator(django_assert_num_queries)
"versions_destroy": True,
"versions_list": True,
"versions_retrieve": True,
"search": True,
}
with django_assert_num_queries(1):
assert document.get_abilities(user) == expected_abilities
@@ -598,6 +605,7 @@ def test_models_documents_get_abilities_editor_user(django_assert_num_queries):
"versions_destroy": False,
"versions_list": True,
"versions_retrieve": True,
"search": True,
}
with django_assert_num_queries(1):
assert document.get_abilities(user) == expected_abilities
@@ -663,6 +671,7 @@ def test_models_documents_get_abilities_reader_user(
"versions_destroy": False,
"versions_list": True,
"versions_retrieve": True,
"search": True,
}
with override_settings(AI_ALLOW_REACH_FROM=ai_access_setting):
@@ -729,6 +738,7 @@ def test_models_documents_get_abilities_commenter_user(
"versions_destroy": False,
"versions_list": True,
"versions_retrieve": True,
"search": True,
}
with override_settings(AI_ALLOW_REACH_FROM=ai_access_setting):
@@ -791,6 +801,7 @@ def test_models_documents_get_abilities_preset_role(django_assert_num_queries):
"versions_destroy": False,
"versions_list": True,
"versions_retrieve": True,
"search": True,
}
@@ -1,5 +1,5 @@
"""
Unit tests for the Document model
Unit tests for FindDocumentIndexer
"""
# pylint: disable=too-many-lines
@@ -12,7 +12,7 @@ from django.db import transaction
import pytest
from core import factories, models
from core.services.search_indexers import SearchIndexer
from core.services.search_indexers import FindDocumentIndexer
pytestmark = pytest.mark.django_db
@@ -30,7 +30,7 @@ def reset_throttle():
reset_batch_indexer_throttle()
@mock.patch.object(SearchIndexer, "push")
@mock.patch.object(FindDocumentIndexer, "push")
@pytest.mark.usefixtures("indexer_settings")
@pytest.mark.django_db(transaction=True)
def test_models_documents_post_save_indexer(mock_push):
@@ -41,7 +41,7 @@ def test_models_documents_post_save_indexer(mock_push):
accesses = {}
data = [call.args[0] for call in mock_push.call_args_list]
indexer = SearchIndexer()
indexer = FindDocumentIndexer()
assert len(data) == 1
@@ -64,14 +64,14 @@ def test_models_documents_post_save_indexer_no_batches(indexer_settings):
"""Test indexation task on doculment creation, no throttle"""
indexer_settings.SEARCH_INDEXER_COUNTDOWN = 0
with mock.patch.object(SearchIndexer, "push") as mock_push:
with mock.patch.object(FindDocumentIndexer, "push") as mock_push:
with transaction.atomic():
doc1, doc2, doc3 = factories.DocumentFactory.create_batch(3)
accesses = {}
data = [call.args[0] for call in mock_push.call_args_list]
indexer = SearchIndexer()
indexer = FindDocumentIndexer()
# 3 calls
assert len(data) == 3
@@ -91,7 +91,7 @@ def test_models_documents_post_save_indexer_no_batches(indexer_settings):
assert cache.get("file-batch-indexer-throttle") is None
@mock.patch.object(SearchIndexer, "push")
@mock.patch.object(FindDocumentIndexer, "push")
@pytest.mark.django_db(transaction=True)
def test_models_documents_post_save_indexer_not_configured(mock_push, indexer_settings):
"""Task should not start an indexation when disabled"""
@@ -106,13 +106,13 @@ def test_models_documents_post_save_indexer_not_configured(mock_push, indexer_se
assert mock_push.assert_not_called
@mock.patch.object(SearchIndexer, "push")
@mock.patch.object(FindDocumentIndexer, "push")
@pytest.mark.django_db(transaction=True)
def test_models_documents_post_save_indexer_wrongly_configured(
mock_push, indexer_settings
):
"""Task should not start an indexation when disabled"""
indexer_settings.SEARCH_INDEXER_URL = None
indexer_settings.INDEXING_URL = None
user = factories.UserFactory()
@@ -123,7 +123,7 @@ def test_models_documents_post_save_indexer_wrongly_configured(
assert mock_push.assert_not_called
@mock.patch.object(SearchIndexer, "push")
@mock.patch.object(FindDocumentIndexer, "push")
@pytest.mark.usefixtures("indexer_settings")
@pytest.mark.django_db(transaction=True)
def test_models_documents_post_save_indexer_with_accesses(mock_push):
@@ -145,7 +145,7 @@ def test_models_documents_post_save_indexer_with_accesses(mock_push):
data = [call.args[0] for call in mock_push.call_args_list]
indexer = SearchIndexer()
indexer = FindDocumentIndexer()
assert len(data) == 1
assert sorted(data[0], key=itemgetter("id")) == sorted(
@@ -158,7 +158,7 @@ def test_models_documents_post_save_indexer_with_accesses(mock_push):
)
@mock.patch.object(SearchIndexer, "push")
@mock.patch.object(FindDocumentIndexer, "push")
@pytest.mark.usefixtures("indexer_settings")
@pytest.mark.django_db(transaction=True)
def test_models_documents_post_save_indexer_deleted(mock_push):
@@ -207,7 +207,7 @@ def test_models_documents_post_save_indexer_deleted(mock_push):
data = [call.args[0] for call in mock_push.call_args_list]
indexer = SearchIndexer()
indexer = FindDocumentIndexer()
assert len(data) == 2
@@ -244,14 +244,14 @@ def test_models_documents_indexer_hard_deleted():
factories.UserDocumentAccessFactory(document=doc, user=user)
# Call task on deleted document.
with mock.patch.object(SearchIndexer, "push") as mock_push:
with mock.patch.object(FindDocumentIndexer, "push") as mock_push:
doc.delete()
# Hard delete document are not re-indexed.
assert mock_push.assert_not_called
@mock.patch.object(SearchIndexer, "push")
@mock.patch.object(FindDocumentIndexer, "push")
@pytest.mark.usefixtures("indexer_settings")
@pytest.mark.django_db(transaction=True)
def test_models_documents_post_save_indexer_restored(mock_push):
@@ -308,7 +308,7 @@ def test_models_documents_post_save_indexer_restored(mock_push):
data = [call.args[0] for call in mock_push.call_args_list]
indexer = SearchIndexer()
indexer = FindDocumentIndexer()
# All docs are re-indexed
assert len(data) == 2
@@ -337,16 +337,16 @@ def test_models_documents_post_save_indexer_restored(mock_push):
@pytest.mark.usefixtures("indexer_settings")
def test_models_documents_post_save_indexer_throttle():
"""Test indexation task skipping on document update"""
indexer = SearchIndexer()
indexer = FindDocumentIndexer()
user = factories.UserFactory()
with mock.patch.object(SearchIndexer, "push"):
with mock.patch.object(FindDocumentIndexer, "push"):
with transaction.atomic():
docs = factories.DocumentFactory.create_batch(5, users=(user,))
accesses = {str(item.path): {"users": [user.sub]} for item in docs}
with mock.patch.object(SearchIndexer, "push") as mock_push:
with mock.patch.object(FindDocumentIndexer, "push") as mock_push:
# Simulate 1 running task
cache.set("document-batch-indexer-throttle", 1)
@@ -359,7 +359,7 @@ def test_models_documents_post_save_indexer_throttle():
assert [call.args[0] for call in mock_push.call_args_list] == []
with mock.patch.object(SearchIndexer, "push") as mock_push:
with mock.patch.object(FindDocumentIndexer, "push") as mock_push:
# No waiting task
cache.delete("document-batch-indexer-throttle")
@@ -389,7 +389,7 @@ def test_models_documents_access_post_save_indexer():
"""Test indexation task on DocumentAccess update"""
users = factories.UserFactory.create_batch(3)
with mock.patch.object(SearchIndexer, "push"):
with mock.patch.object(FindDocumentIndexer, "push"):
with transaction.atomic():
doc = factories.DocumentFactory(users=users)
doc_accesses = models.DocumentAccess.objects.filter(document=doc).order_by(
@@ -398,7 +398,7 @@ def test_models_documents_access_post_save_indexer():
reset_batch_indexer_throttle()
with mock.patch.object(SearchIndexer, "push") as mock_push:
with mock.patch.object(FindDocumentIndexer, "push") as mock_push:
with transaction.atomic():
for doc_access in doc_accesses:
doc_access.save()
@@ -426,7 +426,7 @@ def test_models_items_access_post_save_indexer_no_throttle(indexer_settings):
reset_batch_indexer_throttle()
with mock.patch.object(SearchIndexer, "push") as mock_push:
with mock.patch.object(FindDocumentIndexer, "push") as mock_push:
with transaction.atomic():
for doc_access in doc_accesses:
doc_access.save()
@@ -439,3 +439,70 @@ def test_models_items_access_post_save_indexer_no_throttle(indexer_settings):
assert [len(d) for d in data] == [1] * 3
# the same document is indexed 3 times
assert [d[0]["id"] for d in data] == [str(doc.pk)] * 3
@mock.patch.object(FindDocumentIndexer, "search_query")
@pytest.mark.usefixtures("indexer_settings")
def test_find_document_indexer_search(mock_search_query):
"""Test search function of FindDocumentIndexer returns formatted results"""
# Mock API response from Find
hits = [
{
"_id": "doc-123",
"_source": {
"title": "Test Document",
"content": "This is test content",
"updated_at": "2024-01-01T00:00:00Z",
"path": "/some/path/doc-123",
},
},
{
"_id": "doc-456",
"_source": {
"title.fr": "Document de test",
"content": "Contenu de test",
"updated_at": "2024-01-02T00:00:00Z",
},
},
]
mock_search_query.return_value = hits
q = "test"
token = "fake-token"
nb_results = 10
path = "/some/path/"
visited = ["doc-123"]
results = FindDocumentIndexer().search(
q=q, token=token, nb_results=nb_results, path=path, visited=visited
)
mock_search_query.assert_called_once()
call_args = mock_search_query.call_args
assert call_args[1]["data"] == {
"q": q,
"visited": visited,
"services": ["docs"],
"nb_results": nb_results,
"order_by": "updated_at",
"order_direction": "desc",
"path": path,
}
assert len(results) == 2
assert results == [
{
"id": hits[0]["_id"],
"title": hits[0]["_source"]["title"],
"content": hits[0]["_source"]["content"],
"updated_at": hits[0]["_source"]["updated_at"],
"path": hits[0]["_source"]["path"],
},
{
"id": hits[1]["_id"],
"title": hits[1]["_source"]["title.fr"],
"title.fr": hits[1]["_source"]["title.fr"], # <- Find response artefact
"content": hits[1]["_source"]["content"],
"updated_at": hits[1]["_source"]["updated_at"],
},
]
@@ -15,7 +15,7 @@ from requests import HTTPError
from core import factories, models, utils
from core.services.search_indexers import (
BaseDocumentIndexer,
SearchIndexer,
FindDocumentIndexer,
get_document_indexer,
get_visited_document_ids_of,
)
@@ -78,41 +78,41 @@ def test_services_search_indexer_is_configured(indexer_settings):
# Valid class
indexer_settings.SEARCH_INDEXER_CLASS = (
"core.services.search_indexers.SearchIndexer"
"core.services.search_indexers.FindDocumentIndexer"
)
get_document_indexer.cache_clear()
assert get_document_indexer() is not None
indexer_settings.SEARCH_INDEXER_URL = ""
indexer_settings.INDEXING_URL = ""
# Invalid url
get_document_indexer.cache_clear()
assert not get_document_indexer()
def test_services_search_indexer_url_is_none(indexer_settings):
def test_services_indexing_url_is_none(indexer_settings):
"""
Indexer should raise RuntimeError if SEARCH_INDEXER_URL is None or empty.
Indexer should raise RuntimeError if INDEXING_URL is None or empty.
"""
indexer_settings.SEARCH_INDEXER_URL = None
indexer_settings.INDEXING_URL = None
with pytest.raises(ImproperlyConfigured) as exc_info:
SearchIndexer()
FindDocumentIndexer()
assert "SEARCH_INDEXER_URL must be set in Django settings." in str(exc_info.value)
assert "INDEXING_URL must be set in Django settings." in str(exc_info.value)
def test_services_search_indexer_url_is_empty(indexer_settings):
def test_services_indexing_url_is_empty(indexer_settings):
"""
Indexer should raise RuntimeError if SEARCH_INDEXER_URL is empty string.
Indexer should raise RuntimeError if INDEXING_URL is empty string.
"""
indexer_settings.SEARCH_INDEXER_URL = ""
indexer_settings.INDEXING_URL = ""
with pytest.raises(ImproperlyConfigured) as exc_info:
SearchIndexer()
FindDocumentIndexer()
assert "SEARCH_INDEXER_URL must be set in Django settings." in str(exc_info.value)
assert "INDEXING_URL must be set in Django settings." in str(exc_info.value)
def test_services_search_indexer_secret_is_none(indexer_settings):
@@ -122,7 +122,7 @@ def test_services_search_indexer_secret_is_none(indexer_settings):
indexer_settings.SEARCH_INDEXER_SECRET = None
with pytest.raises(ImproperlyConfigured) as exc_info:
SearchIndexer()
FindDocumentIndexer()
assert "SEARCH_INDEXER_SECRET must be set in Django settings." in str(
exc_info.value
@@ -136,39 +136,35 @@ def test_services_search_indexer_secret_is_empty(indexer_settings):
indexer_settings.SEARCH_INDEXER_SECRET = ""
with pytest.raises(ImproperlyConfigured) as exc_info:
SearchIndexer()
FindDocumentIndexer()
assert "SEARCH_INDEXER_SECRET must be set in Django settings." in str(
exc_info.value
)
def test_services_search_endpoint_is_none(indexer_settings):
def test_services_search_url_is_none(indexer_settings):
"""
Indexer should raise RuntimeError if SEARCH_INDEXER_QUERY_URL is None.
Indexer should raise RuntimeError if SEARCH_URL is None.
"""
indexer_settings.SEARCH_INDEXER_QUERY_URL = None
indexer_settings.SEARCH_URL = None
with pytest.raises(ImproperlyConfigured) as exc_info:
SearchIndexer()
FindDocumentIndexer()
assert "SEARCH_INDEXER_QUERY_URL must be set in Django settings." in str(
exc_info.value
)
assert "SEARCH_URL must be set in Django settings." in str(exc_info.value)
def test_services_search_endpoint_is_empty(indexer_settings):
def test_services_search_url_is_empty(indexer_settings):
"""
Indexer should raise RuntimeError if SEARCH_INDEXER_QUERY_URL is empty.
Indexer should raise RuntimeError if SEARCH_URL is empty.
"""
indexer_settings.SEARCH_INDEXER_QUERY_URL = ""
indexer_settings.SEARCH_URL = ""
with pytest.raises(ImproperlyConfigured) as exc_info:
SearchIndexer()
FindDocumentIndexer()
assert "SEARCH_INDEXER_QUERY_URL must be set in Django settings." in str(
exc_info.value
)
assert "SEARCH_URL must be set in Django settings." in str(exc_info.value)
@pytest.mark.usefixtures("indexer_settings")
@@ -192,7 +188,7 @@ def test_services_search_indexers_serialize_document_returns_expected_json():
}
}
indexer = SearchIndexer()
indexer = FindDocumentIndexer()
result = indexer.serialize_document(document, accesses)
assert set(result.pop("users")) == {str(user_a.sub), str(user_b.sub)}
@@ -221,7 +217,7 @@ def test_services_search_indexers_serialize_document_deleted():
parent.soft_delete()
document.refresh_from_db()
indexer = SearchIndexer()
indexer = FindDocumentIndexer()
result = indexer.serialize_document(document, {})
assert result["is_active"] is False
@@ -232,7 +228,7 @@ def test_services_search_indexers_serialize_document_empty():
"""Empty documents returns empty content in the serialized json."""
document = factories.DocumentFactory(content="", title=None)
indexer = SearchIndexer()
indexer = FindDocumentIndexer()
result = indexer.serialize_document(document, {})
assert result["content"] == ""
@@ -246,7 +242,7 @@ def test_services_search_indexers_index_errors(indexer_settings):
"""
factories.DocumentFactory()
indexer_settings.SEARCH_INDEXER_URL = "http://app-find/api/v1.0/documents/index/"
indexer_settings.INDEXING_URL = "http://app-find/api/v1.0/documents/index/"
responses.add(
responses.POST,
@@ -256,10 +252,10 @@ def test_services_search_indexers_index_errors(indexer_settings):
)
with pytest.raises(HTTPError):
SearchIndexer().index()
FindDocumentIndexer().index()
@patch.object(SearchIndexer, "push")
@patch.object(FindDocumentIndexer, "push")
def test_services_search_indexers_batches_pass_only_batch_accesses(
mock_push, indexer_settings
):
@@ -276,7 +272,7 @@ def test_services_search_indexers_batches_pass_only_batch_accesses(
access = factories.UserDocumentAccessFactory(document=document)
expected_user_subs[str(document.id)] = str(access.user.sub)
assert SearchIndexer().index() == 5
assert FindDocumentIndexer().index() == 5
# Should be 3 batches: 2 + 2 + 1
assert mock_push.call_count == 3
@@ -299,7 +295,7 @@ def test_services_search_indexers_batches_pass_only_batch_accesses(
assert seen_doc_ids == {str(d.id) for d in documents}
@patch.object(SearchIndexer, "push")
@patch.object(FindDocumentIndexer, "push")
@pytest.mark.usefixtures("indexer_settings")
def test_services_search_indexers_batch_size_argument(mock_push):
"""
@@ -314,7 +310,7 @@ def test_services_search_indexers_batch_size_argument(mock_push):
access = factories.UserDocumentAccessFactory(document=document)
expected_user_subs[str(document.id)] = str(access.user.sub)
assert SearchIndexer().index(batch_size=2) == 5
assert FindDocumentIndexer().index(batch_size=2) == 5
# Should be 3 batches: 2 + 2 + 1
assert mock_push.call_count == 3
@@ -337,7 +333,7 @@ def test_services_search_indexers_batch_size_argument(mock_push):
assert seen_doc_ids == {str(d.id) for d in documents}
@patch.object(SearchIndexer, "push")
@patch.object(FindDocumentIndexer, "push")
@pytest.mark.usefixtures("indexer_settings")
def test_services_search_indexers_ignore_empty_documents(mock_push):
"""
@@ -349,7 +345,7 @@ def test_services_search_indexers_ignore_empty_documents(mock_push):
empty_title = factories.DocumentFactory(title="")
empty_content = factories.DocumentFactory(content="")
assert SearchIndexer().index() == 3
assert FindDocumentIndexer().index() == 3
assert mock_push.call_count == 1
@@ -365,7 +361,7 @@ def test_services_search_indexers_ignore_empty_documents(mock_push):
}
@patch.object(SearchIndexer, "push")
@patch.object(FindDocumentIndexer, "push")
def test_services_search_indexers_skip_empty_batches(mock_push, indexer_settings):
"""
Documents indexing batch can be empty if all the docs are empty.
@@ -377,14 +373,14 @@ def test_services_search_indexers_skip_empty_batches(mock_push, indexer_settings
# Only empty docs
factories.DocumentFactory.create_batch(5, content="", title="")
assert SearchIndexer().index() == 1
assert FindDocumentIndexer().index() == 1
assert mock_push.call_count == 1
results = [doc["id"] for doc in mock_push.call_args[0][0]]
assert results == [str(document.id)]
@patch.object(SearchIndexer, "push")
@patch.object(FindDocumentIndexer, "push")
@pytest.mark.usefixtures("indexer_settings")
def test_services_search_indexers_ancestors_link_reach(mock_push):
"""Document accesses and reach should take into account ancestors link reaches."""
@@ -395,7 +391,7 @@ def test_services_search_indexers_ancestors_link_reach(mock_push):
parent = factories.DocumentFactory(parent=grand_parent, link_reach="public")
document = factories.DocumentFactory(parent=parent, link_reach="restricted")
assert SearchIndexer().index() == 4
assert FindDocumentIndexer().index() == 4
results = {doc["id"]: doc for doc in mock_push.call_args[0][0]}
assert len(results) == 4
@@ -405,7 +401,7 @@ def test_services_search_indexers_ancestors_link_reach(mock_push):
assert results[str(document.id)]["reach"] == "public"
@patch.object(SearchIndexer, "push")
@patch.object(FindDocumentIndexer, "push")
@pytest.mark.usefixtures("indexer_settings")
def test_services_search_indexers_ancestors_users(mock_push):
"""Document accesses and reach should include users from ancestors."""
@@ -415,7 +411,7 @@ def test_services_search_indexers_ancestors_users(mock_push):
parent = factories.DocumentFactory(parent=grand_parent, users=[user_p])
document = factories.DocumentFactory(parent=parent, users=[user_d])
assert SearchIndexer().index() == 3
assert FindDocumentIndexer().index() == 3
results = {doc["id"]: doc for doc in mock_push.call_args[0][0]}
assert len(results) == 3
@@ -428,7 +424,7 @@ def test_services_search_indexers_ancestors_users(mock_push):
}
@patch.object(SearchIndexer, "push")
@patch.object(FindDocumentIndexer, "push")
@pytest.mark.usefixtures("indexer_settings")
def test_services_search_indexers_ancestors_teams(mock_push):
"""Document accesses and reach should include teams from ancestors."""
@@ -436,7 +432,7 @@ def test_services_search_indexers_ancestors_teams(mock_push):
parent = factories.DocumentFactory(parent=grand_parent, teams=["team_p"])
document = factories.DocumentFactory(parent=parent, teams=["team_d"])
assert SearchIndexer().index() == 3
assert FindDocumentIndexer().index() == 3
results = {doc["id"]: doc for doc in mock_push.call_args[0][0]}
assert len(results) == 3
@@ -451,9 +447,9 @@ def test_push_uses_correct_url_and_data(mock_post, indexer_settings):
push() should call requests.post with the correct URL from settings
the timeout set to 10 seconds and the data as JSON.
"""
indexer_settings.SEARCH_INDEXER_URL = "http://example.com/index"
indexer_settings.INDEXING_URL = "http://example.com/index"
indexer = SearchIndexer()
indexer = FindDocumentIndexer()
sample_data = [{"id": "123", "title": "Test"}]
mock_response = mock_post.return_value
@@ -464,7 +460,7 @@ def test_push_uses_correct_url_and_data(mock_post, indexer_settings):
mock_post.assert_called_once()
args, kwargs = mock_post.call_args
assert args[0] == indexer_settings.SEARCH_INDEXER_URL
assert args[0] == indexer_settings.INDEXING_URL
assert kwargs.get("json") == sample_data
assert kwargs.get("timeout") == 10
@@ -542,9 +538,7 @@ def test_services_search_indexers_search_errors(indexer_settings):
"""
factories.DocumentFactory()
indexer_settings.SEARCH_INDEXER_QUERY_URL = (
"http://app-find/api/v1.0/documents/search/"
)
indexer_settings.SEARCH_URL = "http://app-find/api/v1.0/documents/search/"
responses.add(
responses.POST,
@@ -554,17 +548,17 @@ def test_services_search_indexers_search_errors(indexer_settings):
)
with pytest.raises(HTTPError):
SearchIndexer().search("alpha", token="mytoken")
FindDocumentIndexer().search("alpha", token="mytoken")
@patch("requests.post")
def test_services_search_indexers_search(mock_post, indexer_settings):
"""
search() should call requests.post to SEARCH_INDEXER_QUERY_URL with the
search() should call requests.post to SEARCH_URL with the
document ids from linktraces.
"""
user = factories.UserFactory()
indexer = SearchIndexer()
indexer = FindDocumentIndexer()
mock_response = mock_post.return_value
mock_response.raise_for_status.return_value = None # No error
@@ -582,7 +576,7 @@ def test_services_search_indexers_search(mock_post, indexer_settings):
args, kwargs = mock_post.call_args
assert args[0] == indexer_settings.SEARCH_INDEXER_QUERY_URL
assert args[0] == indexer_settings.SEARCH_URL
query_data = kwargs.get("json")
assert query_data["q"] == "alpha"
@@ -605,7 +599,7 @@ def test_services_search_indexers_search_nb_results(mock_post, indexer_settings)
indexer_settings.SEARCH_INDEXER_QUERY_LIMIT = 25
user = factories.UserFactory()
indexer = SearchIndexer()
indexer = FindDocumentIndexer()
mock_response = mock_post.return_value
mock_response.raise_for_status.return_value = None # No error
@@ -623,7 +617,7 @@ def test_services_search_indexers_search_nb_results(mock_post, indexer_settings)
args, kwargs = mock_post.call_args
assert args[0] == indexer_settings.SEARCH_INDEXER_QUERY_URL
assert args[0] == indexer_settings.SEARCH_URL
assert kwargs.get("json")["nb_results"] == 25
# The argument overrides the setting value
@@ -631,5 +625,53 @@ def test_services_search_indexers_search_nb_results(mock_post, indexer_settings)
args, kwargs = mock_post.call_args
assert args[0] == indexer_settings.SEARCH_INDEXER_QUERY_URL
assert args[0] == indexer_settings.SEARCH_URL
assert kwargs.get("json")["nb_results"] == 109
def test_search_indexer_get_title_with_localized_field():
"""Test extracting title from localized title field."""
source = {"title.extension": "Bonjour", "id": 1, "content": "test"}
result = FindDocumentIndexer.get_title(source)
assert result == "Bonjour"
def test_search_indexer_get_title_with_multiple_localized_fields():
"""Test that first matching localized title is returned."""
source = {"title.extension": "Bonjour", "title.en": "Hello", "id": 1}
result = FindDocumentIndexer.get_title(source)
assert result in ["Bonjour", "Hello"]
def test_search_indexer_get_title_fallback_to_plain_title():
"""Test fallback to plain 'title' field when no localized field exists."""
source = {"title": "Hello World", "id": 1}
result = FindDocumentIndexer.get_title(source)
assert result == "Hello World"
def test_search_indexer_get_title_no_title_field():
"""Test that empty string is returned when no title field exists."""
source = {"id": 1, "content": "test"}
result = FindDocumentIndexer.get_title(source)
assert result == ""
def test_search_indexer_get_title_with_empty_localized_title():
"""Test that fallback works when localized title is empty."""
source = {"title.extension": "", "title": "Fallback Title", "id": 1}
result = FindDocumentIndexer.get_title(source)
assert result == "Fallback Title"
def test_search_indexer_get_title_with_multiple_extension():
"""Test extracting title from title field with multiple extensions."""
source = {"title.extension_1.extension_2": "Bonjour", "id": 1, "content": "test"}
result = FindDocumentIndexer.get_title(source)
assert result == "Bonjour"
+35
View File
@@ -205,3 +205,38 @@ def test_utils_users_sharing_documents_with_empty_result():
cached_data = cache.get(cache_key)
assert cached_data == {}
def test_utils_get_value_by_pattern_matching_key():
"""Test extracting value from a dictionary with a matching key pattern."""
data = {"title.extension": "Bonjour", "id": 1, "content": "test"}
result = utils.get_value_by_pattern(data, r"^title\.")
assert set(result) == {"Bonjour"}
def test_utils_get_value_by_pattern_multiple_matches():
"""Test that all matching keys are returned."""
data = {"title.extension_1": "Bonjour", "title.extension_2": "Hello", "id": 1}
result = utils.get_value_by_pattern(data, r"^title\.")
assert set(result) == {
"Bonjour",
"Hello",
}
def test_utils_get_value_by_pattern_multiple_extensions():
"""Test that all matching keys are returned."""
data = {"title.extension_1.extension_2": "Bonjour", "id": 1}
result = utils.get_value_by_pattern(data, r"^title\.")
assert set(result) == {"Bonjour"}
def test_utils_get_value_by_pattern_no_match():
"""Test that empty list is returned when no key matches the pattern."""
data = {"name": "Test", "id": 1}
result = utils.get_value_by_pattern(data, r"^title\.")
assert result == []