Harden federated compose against malformed member indexes (REUSE-WP-0020)

Repointing the production hub's 50 Gitea-hosted federation sources to Forgejo
ahead of the 2026-08-31 CoulombCore retirement took /v1/federated to HTTP 500.
One member index (evidence-binder) has capability rows with no `id`, and
compose_federated_index dereferenced item["id"] unguarded. Its Gitea copy was a
stale snapshot returning a non-mapping, so those rows had never been parsed.

A single malformed member index must not take down the whole endpoint. Extract
_read_index_entries(): unparseable YAML, a non-mapping body, an empty file, and
a non-list `capabilities` each degrade to a warning and an empty row list, and
rows without an `id` are skipped individually. A failed source stays listed with
count 0 so it remains visible to operators rather than silently disappearing.

Also fix wall-clock rot in tests/test_plan_check.py, which was already failing
at clean HEAD: three tests pinned the compose date to a literal that has now
aged past STALE_DAYS.

Add workplan REUSE-WP-0020 covering the full cutover.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
This commit is contained in:
tegwick 2026-08-21 00:04:39 +02:00
parent fa1235474f
commit 0c6b1e2538
5 changed files with 403 additions and 16 deletions

View file

@ -205,4 +205,81 @@ def test_compose_merges_remote_capabilities(tmp_path, monkeypatch):
def test_load_production_manifest_still_validates():
manifest = load_federation_manifest()
assert manifest["domain"] == "helix_forge"
assert any(source["repo"] == "reuse-surface" for source in manifest["sources"])
assert any(source["repo"] == "reuse-surface" for source in manifest["sources"])
def _compose_with_remote_body(body: str, tmp_path, monkeypatch):
"""Compose with the remote member index serving `body` verbatim."""
monkeypatch.setattr("reuse_surface.federation.CACHE_DIR", tmp_path / "cache")
payload = body.encode("utf-8")
class FakeResponse:
def __enter__(self):
return self
def __exit__(self, *args):
return False
def read(self):
return payload
with patch("urllib.request.urlopen", return_value=FakeResponse()):
return compose_federated_index(_remote_manifest())
def _local_ids_survived(federated) -> bool:
return any(item["source_repo"] == "local" for item in federated["capabilities"])
def test_compose_skips_capability_without_id(tmp_path, monkeypatch):
body = """
version: 1
domain: helix_forge
capabilities:
- type: library
title: No id at all
- id: capability.remote.sample
name: Remote Sample
"""
federated, warnings = _compose_with_remote_body(body, tmp_path, monkeypatch)
ids = {item["id"] for item in federated["capabilities"]}
assert "capability.remote.sample" in ids
assert _local_ids_survived(federated)
assert any("remote-repo" in w and "no id" in w for w in warnings)
def test_compose_skips_non_mapping_index(tmp_path, monkeypatch):
federated, warnings = _compose_with_remote_body(
"just a string, not a mapping\n", tmp_path, monkeypatch
)
assert _local_ids_survived(federated)
assert any("not a mapping" in w for w in warnings)
def test_compose_skips_empty_index(tmp_path, monkeypatch):
federated, warnings = _compose_with_remote_body("", tmp_path, monkeypatch)
assert _local_ids_survived(federated)
assert any("remote-repo" in w for w in warnings)
def test_compose_skips_unparseable_index(tmp_path, monkeypatch):
federated, warnings = _compose_with_remote_body(
"capabilities: [unclosed\n", tmp_path, monkeypatch
)
assert _local_ids_survived(federated)
assert any("unparseable" in w for w in warnings)
def test_compose_skips_capabilities_not_a_list(tmp_path, monkeypatch):
federated, warnings = _compose_with_remote_body(
"version: 1\ncapabilities: not-a-list\n", tmp_path, monkeypatch
)
assert _local_ids_survived(federated)
assert any("not a list" in w for w in warnings)
def test_malformed_source_still_listed_with_zero_count(tmp_path, monkeypatch):
federated, _ = _compose_with_remote_body(
"just a string, not a mapping\n", tmp_path, monkeypatch
)
remote = next(s for s in federated["sources"] if s["repo"] == "remote-repo")
assert remote["count"] == 0