keep a precise failure precise, and state one redirect policy
Two problems of the same shape: information about *why* something failed being replaced by something vaguer. get_dataset_geojson wrapped the JSON parse, the metadata read, the CRS resolution and the canonicalisation in one try and reported all of it as "Stored dataset is not valid JSON" with a 500. An operator whose dataset had an unusable CRS was sent to inspect a file that parses perfectly well, and the canonicaliser's own AppError — with its code and its status — never reached them. Only the parse is now inside that handler; everything after it keeps the error it raised, and a genuine bug becomes a distinct 500 rather than a mislabelled client error. A guard finds the same shape elsewhere: catching Exception around a call into another component and relabelling what it reported. Wrapping one's own private helper stays legitimate and the guard says so. The redirect policy was split without anyone saying so. Two acquisition services rejected every redirect through a hand-rolled opener, while eight allowed a same-origin one through the shared guard — and only the latter checked where the response came from. Both live in the guard now, and the strict path uses the rejecting handler rather than the guard's after-the-fact check: objecting to response.url means urllib already opened the connection and read the body, which for a metadata endpoint is the whole attack. That was a weakening I introduced in this same commit's first draft. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
This commit is contained in:
@@ -162,3 +162,96 @@ class TestTheGuardIsWiredIntoAcquisition:
|
||||
OrthophotoAcquisitionService._fetch("http://192.168.10.150/wms", self._settings())
|
||||
|
||||
assert exc_info.value.code == "OUTBOUND_URL_NOT_ALLOWED"
|
||||
|
||||
|
||||
class TestOneRedirectPolicy:
|
||||
"""Two acquisition services rejected every redirect through their own
|
||||
opener while eight allowed a same-origin one through this guard. Two
|
||||
policies with no stated reason, and only one of them checked where the
|
||||
response actually came from."""
|
||||
|
||||
def test_the_strict_policy_refuses_any_redirect(self) -> None:
|
||||
from app.services.outbound_request_guard import guarded_opener
|
||||
|
||||
opener = guarded_opener("https://geo.api.vlaanderen.be/GRB/wfs", allow_redirect=False)
|
||||
|
||||
class _Redirected:
|
||||
url = "https://geo.api.vlaanderen.be/GRB/wfs/v2"
|
||||
|
||||
def __enter__(self):
|
||||
return self
|
||||
|
||||
def __exit__(self, *_args):
|
||||
return False
|
||||
|
||||
with pytest.raises(AppError) as exc_info:
|
||||
with opener(object(), timeout=1, _transport=lambda *_a, **_k: _Redirected()):
|
||||
pass
|
||||
|
||||
assert exc_info.value.code == "OUTBOUND_REDIRECT_NOT_ALLOWED"
|
||||
|
||||
def test_the_strict_policy_still_allows_the_response_it_asked_for(self) -> None:
|
||||
from app.services.outbound_request_guard import guarded_opener
|
||||
|
||||
url = "https://geo.api.vlaanderen.be/GRB/wfs"
|
||||
opener = guarded_opener(url, allow_redirect=False)
|
||||
|
||||
class _Direct:
|
||||
def __init__(self) -> None:
|
||||
self.url = url
|
||||
|
||||
def __enter__(self):
|
||||
return self
|
||||
|
||||
def __exit__(self, *_args):
|
||||
return False
|
||||
|
||||
with opener(object(), timeout=1, _transport=lambda *_a, **_k: _Direct()) as response:
|
||||
assert response.url == url
|
||||
|
||||
def test_both_policies_refuse_a_private_destination(self) -> None:
|
||||
from app.services.outbound_request_guard import guarded_opener
|
||||
|
||||
for allow_redirect in (True, False):
|
||||
with pytest.raises(AppError) as exc_info:
|
||||
guarded_opener("http://10.0.0.5/wfs", allow_redirect=allow_redirect)
|
||||
assert exc_info.value.code == "OUTBOUND_URL_NOT_ALLOWED"
|
||||
|
||||
def test_the_strict_services_use_the_shared_guard(self) -> None:
|
||||
"""Behavioural: their own fetch paths refuse a private endpoint, which
|
||||
the hand-rolled opener never checked."""
|
||||
|
||||
from app.core.config import Settings
|
||||
from app.services.grb_acquisition_service import GrbAcquisitionService
|
||||
from app.services.official_vector_acquisition_service import OfficialVectorAcquisitionService
|
||||
|
||||
settings = Settings(_env_file=None)
|
||||
for service in (GrbAcquisitionService, OfficialVectorAcquisitionService):
|
||||
with pytest.raises(AppError) as exc_info:
|
||||
service._read_page("http://127.0.0.1:9/wfs", settings, None)
|
||||
assert exc_info.value.code == "OUTBOUND_URL_NOT_ALLOWED"
|
||||
|
||||
|
||||
def test_a_refused_redirect_is_never_requested() -> None:
|
||||
"""Rejecting after the fact still sends the request.
|
||||
|
||||
Checking ``response.url`` means urllib has already followed the chain: the
|
||||
connection to the redirect target was opened and the response read. For a
|
||||
destination like a metadata endpoint that is the whole attack. The strict
|
||||
policy must refuse to follow, not refuse afterwards.
|
||||
"""
|
||||
|
||||
from app.services.outbound_request_guard import no_redirect_opener
|
||||
|
||||
opener = no_redirect_opener()
|
||||
handlers = [type(handler).__name__ for handler in opener.handlers]
|
||||
|
||||
assert "_RejectRedirects" in handlers
|
||||
|
||||
|
||||
def test_the_rejecting_handler_returns_no_new_request() -> None:
|
||||
from app.services.outbound_request_guard import _RejectRedirects
|
||||
|
||||
handler = _RejectRedirects()
|
||||
|
||||
assert handler.redirect_request(None, None, 302, "Found", {}, "http://169.254.169.254/") is None
|
||||
|
||||
Reference in New Issue
Block a user