merge: R-B (Crossref references as third citation fallback)

tests/ingest/test_ingest.py

@@ -107,6 +107,60 @@ def test_ingest_paper_basic() -> None:
     )
 
 
+def test_ingest_citation_fallback_to_crossref() -> None:
+    """R-B: OpenAlex + S2 both empty → Crossref references supply the edges.
+
+    Crossref is the third leg of the fallback chain. Its cited DOIs are
+    case-normalised and citing_id is rewritten to the canonical paper.id.
+    """
+    paper = _make_paper(paper_id="10.1007/s00454-019-00132-8", openalex_id="W123")
+    mock_conn = MagicMock()
+    mock_conn.execute = MagicMock()
+    mock_conn.executemany = MagicMock()
+    mock_conn.commit = MagicMock()
+
+    # Upper-case suffix proves the cited DOI is normalised to bare lower-case.
+    crossref_refs = [Citation(citing_id=paper.id, cited_id="10.1090/S0002-9947-04-03545-7")]
+
+    with (
+        patch("codex.ingest.openalex.fetch_paper", return_value=paper),
+        patch("codex.ingest.openalex.fetch_citations", return_value=[]),  # OpenAlex empty
+        patch("codex.ingest.semanticscholar.fetch_references", return_value=[]),  # S2 empty
+        patch("codex.ingest.crossref.fetch_references", return_value=crossref_refs) as mock_cr,
+        patch("codex.ingest.get_embedder", return_value=_fake_embedder()),
+        patch("codex.ingest.get_conn", side_effect=_make_conn_cm(mock_conn)),
+    ):
+        result = ingest_paper(paper.id)
+
+    # Crossref consulted with the bare DOI; one edge upserted.
+    mock_cr.assert_called_once_with(paper.id)
+    assert result.citations_upserted == 1
+    mock_cursor = mock_conn.cursor.return_value.__enter__.return_value
+    cit_rows = mock_cursor.executemany.call_args_list[0][0][1]
+    assert cit_rows[0][0] == paper.id
+    assert cit_rows[0][1] == "10.1090/s0002-9947-04-03545-7"
+
+
+def test_ingest_crossref_not_called_when_openalex_has_citations() -> None:
+    """R-B: the Crossref leg fires only when OpenAlex+S2 are empty (it's a fallback)."""
+    paper = _make_paper(paper_id="10.1007/s00454-019-00132-8", openalex_id="W123")
+    mock_conn = MagicMock()
+
+    with (
+        patch("codex.ingest.openalex.fetch_paper", return_value=paper),
+        patch(
+            "codex.ingest.openalex.fetch_citations",
+            return_value=[Citation(citing_id="W123", cited_id="https://openalex.org/W9")],
+        ),
+        patch("codex.ingest.crossref.fetch_references") as mock_cr,
+        patch("codex.ingest.get_embedder", return_value=_fake_embedder()),
+        patch("codex.ingest.get_conn", side_effect=_make_conn_cm(mock_conn)),
+    ):
+        ingest_paper(paper.id)
+
+    mock_cr.assert_not_called()
+
+
 # ---------------------------------------------------------------------------
 # 2. test_ingest_paper_source_tex
 # ---------------------------------------------------------------------------