s

tests/unit/test_publication_pdf_queue_policy.py

@@ -1,11 +1,14 @@
 from __future__ import annotations
 
 from datetime import datetime, timedelta, timezone
+from types import SimpleNamespace
 
 import pytest
 
 from app.db.models import PublicationPdfJob
 from app.services.domains.publications import pdf_queue
+from app.services.domains.publications.pdf_resolution_pipeline import PipelineOutcome
+from app.services.domains.unpaywall.application import OaResolutionOutcome
 
 
 def _job(
@@ -22,6 +25,25 @@ def _job(
     )
 
 
+def _row(*, pub_url: str | None = "https://scholar.google.com/citations?view_op=view_citation&citation_for_view=abc:xyz") -> SimpleNamespace:
+    return SimpleNamespace(
+        publication_id=1,
+        scholar_profile_id=1,
+        scholar_label="Ada Lovelace",
+        title="A paper",
+        year=2024,
+        citation_count=0,
+        venue_text=None,
+        pub_url=pub_url,
+        doi=None,
+        pdf_url=None,
+        is_read=False,
+        is_favorite=False,
+        first_seen_at=datetime(2026, 2, 22, 12, 0, tzinfo=timezone.utc),
+        is_new_in_latest_run=True,
+    )
+
+
 def test_pdf_queue_auto_enqueue_blocks_recent_attempt(monkeypatch: pytest.MonkeyPatch) -> None:
     now = datetime(2026, 2, 21, 12, 0, tzinfo=timezone.utc)
     monkeypatch.setattr(pdf_queue, "_utcnow", lambda: now)
@@ -107,3 +129,44 @@ def test_pdf_queue_manual_requeue_still_blocks_when_inflight() -> None:
     )
     assert pdf_queue._can_enqueue_job(running, force_retry=True) is False
     assert pdf_queue._can_enqueue_job(queued, force_retry=True) is False
+
+
+@pytest.mark.asyncio
+async def test_fetch_outcome_for_row_uses_pipeline_outcome(monkeypatch: pytest.MonkeyPatch) -> None:
+    async def _fake_pipeline(*, row, request_email=None):
+        assert request_email == "user@example.com"
+        return PipelineOutcome(
+            outcome=OaResolutionOutcome(
+                publication_id=row.publication_id,
+                doi=None,
+                pdf_url="https://arxiv.org/pdf/1703.06103",
+                failure_reason=None,
+                source=pdf_queue.PDF_SOURCE_SCHOLAR_PUBLICATION_PAGE,
+                used_crossref=False,
+            ),
+            scholar_candidates=None,
+        )
+
+    monkeypatch.setattr(pdf_queue, "resolve_publication_pdf_outcome_for_row", _fake_pipeline)
+
+    outcome = await pdf_queue._fetch_outcome_for_row(row=_row(), request_email="user@example.com")
+
+    assert outcome.pdf_url == "https://arxiv.org/pdf/1703.06103"
+    assert outcome.source == pdf_queue.PDF_SOURCE_SCHOLAR_PUBLICATION_PAGE
+    assert outcome.used_crossref is False
+
+
+@pytest.mark.asyncio
+async def test_fetch_outcome_for_row_returns_failed_outcome_when_pipeline_returns_none(
+    monkeypatch: pytest.MonkeyPatch,
+) -> None:
+    async def _fake_pipeline(*, row, request_email=None):
+        assert request_email == "user@example.com"
+        return PipelineOutcome(outcome=None, scholar_candidates=None)
+
+    monkeypatch.setattr(pdf_queue, "resolve_publication_pdf_outcome_for_row", _fake_pipeline)
+
+    outcome = await pdf_queue._fetch_outcome_for_row(row=_row(), request_email="user@example.com")
+
+    assert outcome.pdf_url is None
+    assert outcome.failure_reason == pdf_queue.FAILURE_RESOLUTION_EXCEPTION