scholarr/tests/unit/test_ingestion_arxiv_rate_limit.py
Justin Visser 87aa89b58c fix: resolve mypy errors, fix arxiv test session isolation, and add premerge script
- Remove unused type:ignore comment in scholars.py
- Fix 51 mypy errors across test files (Any return types, cast(), protocol stubs)
- Fix arxiv unit test failures caused by session isolation (patch_session_factory fixture)
- Fix integration test rate-limit bleed between search and create
- Add scripts/premerge.sh for local CI verification
- Add docs/website/.docusaurus/ to .gitignore

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-02 12:46:10 +01:00

49 lines
1.6 KiB
Python

from __future__ import annotations
from types import SimpleNamespace
from typing import Any, cast
import pytest
from app.services.arxiv.errors import ArxivRateLimitError
from app.services.ingestion.enrichment import EnrichmentRunner
from app.services.publication_identifiers import application as identifier_service
@pytest.mark.asyncio
async def test_discover_identifiers_for_enrichment_disables_arxiv_on_rate_limit(
monkeypatch: pytest.MonkeyPatch,
) -> None:
runner = EnrichmentRunner()
publication = SimpleNamespace(id=11, author_text="Ada Lovelace")
calls = {"sync": 0}
async def _raise_rate_limit(db_session, *, publication, scholar_label):
_ = (db_session, publication, scholar_label)
raise ArxivRateLimitError("arXiv rate limit hit (429) — stopping batch")
async def _sync_fields(db_session, *, publication):
_ = (db_session, publication)
calls["sync"] += 1
monkeypatch.setattr(
identifier_service,
"discover_and_sync_identifiers_for_publication",
_raise_rate_limit,
)
monkeypatch.setattr(identifier_service, "sync_identifiers_for_publication_fields", _sync_fields)
async def _publish_noop(*args, **kwargs) -> None:
_ = (args, kwargs)
monkeypatch.setattr(runner, "_publish_identifier_update_event", _publish_noop)
result = await runner._discover_identifiers_for_enrichment(
cast(Any, object()),
publication=cast(Any, publication),
run_id=321,
allow_arxiv_lookup=True,
)
assert result is False
assert calls["sync"] == 1