test(review): cover findings #1 (non-bare caller id) and #4 (backfill connection scope)

#1: assert a URL-form / mixed-case caller id is normalized to the bare canonical form in the papers upsert (the fix's whole point; existing DQ-5 test only used a bare caller). #4: assert ra_grobid_backfill.main() opens two separate connections (read released before the GROBID loop, fresh one for the write) rather than holding one across the loop. Both pass; ruff clean.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
This commit is contained in:
Tarik Moussa
2026-06-27 09:09:39 +02:00
parent b2f01ce010
commit ab621fc5f5
2 changed files with 68 additions and 2 deletions

View File

@@ -829,6 +829,36 @@ def test_ingest_doi_paper_upserts_bare_canonical_id() -> None:
)
def test_ingest_normalizes_non_bare_caller_id() -> None:
"""Review #1: a non-bare CALLER id (URL-form / mixed-case DOI) is normalized to the
bare canonical form before being pinned to papers.id (the C-7 pin runs it through
_norm_cited_id), so a sloppy caller cannot store a URL-form papers.id that would
defeat ON CONFLICT (id) idempotency or the ``paper.id.startswith('10.')`` gates."""
paper = _make_paper(paper_id="10.1007/s00454-019-00132-8", openalex_id="W1")
mock_conn = MagicMock()
mock_conn.execute = MagicMock()
mock_conn.executemany = MagicMock()
mock_conn.commit = MagicMock()
with (
patch("codex.ingest.openalex.fetch_paper", return_value=paper),
patch("codex.ingest.openalex.fetch_citations", return_value=[]),
patch("codex.ingest.semanticscholar.fetch_references", return_value=[]),
patch("codex.ingest.crossref.fetch_references", return_value=[]),
patch("codex.ingest.get_embedder", return_value=_fake_embedder()),
patch("codex.ingest.get_conn", side_effect=_make_conn_cm(mock_conn)),
):
# Caller passes the URL form with an upper-case suffix char (worst case).
result = ingest_paper("https://doi.org/10.1007/S00454-019-00132-8")
bare = "10.1007/s00454-019-00132-8"
assert result.paper_id == bare
upsert_params: dict[str, Any] = mock_conn.execute.call_args_list[0][0][1]
assert upsert_params["id"] == bare, (
f"non-bare caller must be normalized to '{bare}', got '{upsert_params['id']}'"
)
def test_ingest_disambiguates_bibkey_on_unique_violation() -> None:
"""A papers.bibkey UNIQUE collision is retried with an a/b/c suffix (audit C-15)."""
paper = _make_paper() # bibkey auto-generates to "AliceBob2023"