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>

backend/app/services/dataset_service.py

@@ -2906,8 +2906,19 @@ class DatasetService:
             raise AppError(code="DATASET_FILE_MISSING", message="Stored file missing", status_code=404)
 
         raw = load_dataset_text(dataset.storage_path)
+        # Only the parse can be "not valid JSON". Everything after it fails for
+        # its own reasons and must say so, or an operator is sent to inspect a
+        # file that parses perfectly well.
         try:
             payload = json.loads(raw)
+        except Exception as exc:
+            raise AppError(
+                code="INVALID_GEOJSON",
+                message="Stored dataset is not valid JSON",
+                status_code=500,
+            ) from exc
+
+        try:
             metadata_value = getattr(dataset, "metadata_json", None)
             metadata = metadata_value if isinstance(metadata_value, dict) else {}
             provenance_value = getattr(dataset, "provenance_metadata", None)
@@ -2933,8 +2944,17 @@ class DatasetService:
                 )
             )
             return VectorFeatureService.canonicalize_geojson_payload(payload, source_crs=str(source_crs))
+        except AppError:
+            # The canonicaliser's diagnosis is more precise than anything this
+            # layer could substitute for it.
+            raise
         except Exception as exc:
-            raise AppError(code="INVALID_GEOJSON", message="Stored dataset is not valid JSON", status_code=500) from exc
+            raise AppError(
+                code="DATASET_GEOJSON_UNREADABLE",
+                message="The stored dataset could not be read as canonical GeoJSON",
+                details={"dataset_id": str(dataset.id), "error_type": type(exc).__name__},
+                status_code=500,
+            ) from exc
 
     @staticmethod
     def inspect_vector_dataset(db: Session, dataset_id: UUID) -> dict[str, Any]:

backend/app/services/grb_acquisition_service.py

@@ -9,7 +9,7 @@ from pathlib import Path
 from typing import Any, Callable
 from urllib.error import HTTPError, URLError
 from urllib.parse import parse_qsl, urlencode, urljoin, urlparse, urlunparse
-from urllib.request import HTTPRedirectHandler, Request, build_opener
+from urllib.request import Request
 from uuid import UUID
 
 from geoalchemy2.shape import to_shape
@@ -20,20 +20,12 @@ from shapely.validation import make_valid
 
 from app.core.config import Settings, get_settings
 from app.core.errors import AppError
+from app.services.outbound_request_guard import guarded_opener
 from app.models import Area, Dataset, Project
 from app.schemas.grb import GrbAcquireRequest, GrbAcquisitionResult, GrbProductRead
 from app.services.dataset_service import DatasetService
 
 
-class _RejectRedirects(HTTPRedirectHandler):
-    def redirect_request(self, req, fp, code, msg, headers, newurl):
-        del req, fp, code, msg, headers, newurl
-        return None
-
-
-_NO_REDIRECT_OPENER = build_opener(_RejectRedirects())
-
-
 @dataclass(frozen=True)
 class GrbCollection:
     name: str
@@ -368,7 +360,7 @@ class GrbAcquisitionService:
             },
         )
         try:
-            with (opener or _NO_REDIRECT_OPENER.open)(
+            with (opener or guarded_opener(url, allow_redirect=False))(
                 request,
                 timeout=settings.grb_timeout_seconds,
             ) as response:

backend/app/services/official_vector_acquisition_service.py

@@ -10,7 +10,7 @@ import re
 from typing import Any, Callable
 from urllib.error import HTTPError, URLError
 from urllib.parse import urlencode, urlparse
-from urllib.request import HTTPRedirectHandler, Request, build_opener
+from urllib.request import Request
 from uuid import UUID
 
 from geoalchemy2.shape import to_shape
@@ -21,6 +21,7 @@ from shapely.validation import make_valid
 
 from app.core.config import Settings, get_settings
 from app.core.errors import AppError
+from app.services.outbound_request_guard import guarded_opener
 from app.models import Area, Dataset, Project
 from app.schemas.official_vector import (
     OfficialVectorAcquireRequest,
@@ -30,13 +31,6 @@ from app.schemas.official_vector import (
 from app.services.dataset_service import DatasetService
 
 
-class _RejectRedirects(HTTPRedirectHandler):
-    def redirect_request(self, req, fp, code, msg, headers, newurl):
-        del req, fp, code, msg, headers, newurl
-        return None
-
-
-_NO_REDIRECT_OPENER = build_opener(_RejectRedirects())
 _TO_LAMBERT72 = Transformer.from_crs("EPSG:4326", "EPSG:31370", always_xy=True)
 _TO_WGS84 = Transformer.from_crs("EPSG:31370", "EPSG:4326", always_xy=True)
 
@@ -1086,7 +1080,7 @@ class OfficialVectorAcquisitionService:
             },
         )
         try:
-            with (opener or _NO_REDIRECT_OPENER.open)(
+            with (opener or guarded_opener(url, allow_redirect=False))(
                 request,
                 timeout=settings.official_vector_timeout_seconds,
             ) as response:

backend/app/services/outbound_request_guard.py

@@ -18,13 +18,32 @@ import socket
 from collections.abc import Callable
 from typing import Any
 from urllib.parse import urlparse
-from urllib.request import urlopen
+from urllib.request import HTTPRedirectHandler, build_opener, urlopen
 
 from app.core.errors import AppError
 
 ALLOWED_SCHEMES = {"http", "https"}
 
 
+class _RejectRedirects(HTTPRedirectHandler):
+    """Refuse to *follow* a redirect, rather than object after the fact.
+
+    Checking the final URL means urllib already opened the connection and read
+    the response — for a destination like a cloud metadata endpoint that is the
+    whole attack. Returning ``None`` here means the request is never made.
+    """
+
+    def redirect_request(self, req, fp, code, msg, headers, newurl):  # noqa: ANN001, D102
+        del req, fp, code, msg, headers, newurl
+        return None
+
+
+def no_redirect_opener():
+    """An opener that will not follow a redirect anywhere."""
+
+    return build_opener(_RejectRedirects())
+
+
 def _reject(code: str, message: str, **details: Any) -> AppError:
     return AppError(code=code, message=message, details=details or None, status_code=502)
 
@@ -117,20 +136,34 @@ def assert_same_origin_redirect(original_url: str, final_url: str) -> None:
     assert_public_http_url(final_url)
 
 
-def guarded_opener(expected_url: str) -> Callable[..., Any]:
+def guarded_opener(expected_url: str, *, allow_redirect: bool = True) -> Callable[..., Any]:
     """An ``urlopen`` replacement that verifies where the response came from.
 
     ``urlopen`` has already followed the redirect chain by the time it returns,
     so the check is on ``response.url``: the body is still unread, and raising
     here means nothing off-origin is ever parsed or persisted.
+
+    ``allow_redirect=False`` refuses any redirect at all, which is what the
+    paged OGC feature readers want: a page URL they built themselves should be
+    answered by that URL, and a redirect there means the endpoint moved under
+    them mid-pagination.
     """
 
     assert_public_http_url(expected_url)
 
+    default_transport = urlopen if allow_redirect else no_redirect_opener().open
+
     def _open(request: Any, *args: Any, _transport: Callable[..., Any] | None = None, **kwargs: Any) -> Any:
-        response = (_transport or urlopen)(request, *args, **kwargs)
+        response = (_transport or default_transport)(request, *args, **kwargs)
         final_url = str(getattr(response, "url", "") or "")
         try:
+            if not allow_redirect and final_url and final_url != expected_url:
+                raise _reject(
+                    "OUTBOUND_REDIRECT_NOT_ALLOWED",
+                    "The official endpoint redirected; this reader accepts only the URL it requested.",
+                    expected_url=expected_url,
+                    redirect_url=final_url,
+                )
             assert_same_origin_redirect(expected_url, final_url)
         except AppError:
             close = getattr(response, "close", None)