justinzeus/scholarr
1
0
Fork 0
Code Issues 1 Pull requests 18 Projects Releases Packages Wiki Activity Actions

refactor: decompose scholars service and pdf_queue into focused modules

Browse source 
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
Justin Visser 2026-02-27 14:39:12 +01:00
parent 8c6069c121
commit b701583716
10 changed files with 1592 additions and 1443 deletions
Download patch file Download diff file Expand all files Collapse all files

26
tests/unit/test_publication_pdf_queue_policy.py
View file

@ -6,7 +6,7 @@ from types import SimpleNamespace
import pytest
from app.db.models import PublicationPdfJob
from app.services.publications import pdf_queue
from app.services.publications import pdf_queue, pdf_queue_resolution
from app.services.publications.pdf_resolution_pipeline import PipelineOutcome
from app.services.unpaywall.application import OaResolutionOutcome
@ -150,9 +150,9 @@ async def test_fetch_outcome_for_row_uses_pipeline_outcome(monkeypatch: pytest.M
scholar_candidates=None,
)
monkeypatch.setattr(pdf_queue, "resolve_publication_pdf_outcome_for_row", _fake_pipeline)
monkeypatch.setattr(pdf_queue_resolution, "resolve_publication_pdf_outcome_for_row", _fake_pipeline)
outcome, arxiv_rate_limited = await pdf_queue._fetch_outcome_for_row(
outcome, arxiv_rate_limited = await pdf_queue_resolution._fetch_outcome_for_row(
row=_row(),
request_email="user@example.com",
)
@ -172,15 +172,15 @@ async def test_fetch_outcome_for_row_returns_failed_outcome_when_pipeline_return
assert allow_arxiv_lookup is True
return PipelineOutcome(outcome=None, scholar_candidates=None, arxiv_rate_limited=True)
monkeypatch.setattr(pdf_queue, "resolve_publication_pdf_outcome_for_row", _fake_pipeline)
monkeypatch.setattr(pdf_queue_resolution, "resolve_publication_pdf_outcome_for_row", _fake_pipeline)
outcome, arxiv_rate_limited = await pdf_queue._fetch_outcome_for_row(
outcome, arxiv_rate_limited = await pdf_queue_resolution._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
assert outcome.failure_reason == pdf_queue_resolution.FAILURE_RESOLUTION_EXCEPTION
assert arxiv_rate_limited is True
@ -210,11 +210,11 @@ async def test_resolve_publication_row_persists_outcome_and_returns_rate_limit_f
async def _capture_persist_outcome(*, publication_id: int, user_id: int, outcome: OaResolutionOutcome) -> None:
captured.append((publication_id, user_id, outcome))
monkeypatch.setattr(pdf_queue, "_mark_attempt_started", _noop_mark_attempt_started)
monkeypatch.setattr(pdf_queue, "_fetch_outcome_for_row", _fake_fetch)
monkeypatch.setattr(pdf_queue, "_persist_outcome", _capture_persist_outcome)
monkeypatch.setattr(pdf_queue_resolution, "_mark_attempt_started", _noop_mark_attempt_started)
monkeypatch.setattr(pdf_queue_resolution, "_fetch_outcome_for_row", _fake_fetch)
monkeypatch.setattr(pdf_queue_resolution, "_persist_outcome", _capture_persist_outcome)
rate_limited = await pdf_queue._resolve_publication_row(
rate_limited = await pdf_queue_resolution._resolve_publication_row(
user_id=42,
request_email="user@example.com",
row=_row(),
@ -252,10 +252,10 @@ async def test_run_resolution_task_disables_arxiv_for_remaining_batch(
calls.append((int(row.publication_id), bool(allow_arxiv_lookup)))
return row.publication_id == 1
monkeypatch.setattr(pdf_queue, "get_session_factory", _raise_session_factory_error)
monkeypatch.setattr(pdf_queue, "_resolve_publication_row", _fake_resolve_publication_row)
monkeypatch.setattr(pdf_queue_resolution, "get_session_factory", _raise_session_factory_error)
monkeypatch.setattr(pdf_queue_resolution, "_resolve_publication_row", _fake_resolve_publication_row)
await pdf_queue._run_resolution_task(
await pdf_queue_resolution._run_resolution_task(
user_id=42,
request_email="user@example.com",
rows=[first, second],