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

ci: add ruff linting and mypy type checking

Browse source 
Add ruff and mypy to dev dependencies with configuration in pyproject.toml.
Add a lint CI job that runs ruff check, ruff format --check, and mypy.
Auto-fix import sorting and formatting across the codebase. Exclude
alembic/versions from linting (auto-generated migrations). Ignore B008
(FastAPI Depends pattern) and RUF001 (unicode in user-facing strings).

21 ruff lint errors and 50 mypy errors remain for manual review.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
Justin Visser 2026-02-26 22:11:41 +01:00
parent 399276ea69
commit bf04c77aa9
137 changed files with 3066 additions and 1900 deletions
Download patch file Download diff file Expand all files Collapse all files

9
tests/unit/services/domains/arxiv/test_cache.py
View file

@ -2,7 +2,7 @@ from __future__ import annotations
import asyncio
import gc
from datetime import datetime, timedelta, timezone
from datetime import UTC, datetime, timedelta
import pytest
from sqlalchemy import select
@ -59,7 +59,7 @@ def test_build_query_fingerprint_normalizes_search_and_id_params() -> None:
@pytest.mark.asyncio
async def test_cache_entry_expires_and_is_deleted(db_session: AsyncSession) -> None:
query_fingerprint = build_query_fingerprint(params={"search_query": "ti:test", "start": 0})
now_utc = datetime(2026, 2, 26, 12, 0, tzinfo=timezone.utc)
now_utc = datetime(2026, 2, 26, 12, 0, tzinfo=UTC)
await set_cached_feed(
query_fingerprint=query_fingerprint,
@ -79,9 +79,7 @@ async def test_cache_entry_expires_and_is_deleted(db_session: AsyncSession) -> N
)
result = await db_session.execute(
select(ArxivQueryCacheEntry).where(
ArxivQueryCacheEntry.query_fingerprint == query_fingerprint
)
select(ArxivQueryCacheEntry).where(ArxivQueryCacheEntry.query_fingerprint == query_fingerprint)
)
assert hit is not None
assert miss is None
@ -118,6 +116,7 @@ async def test_inflight_owner_failure_without_joiner_has_no_unretrieved_exceptio
loop.set_exception_handler(_capture_exception)
try:
async def _failing_fetch() -> ArxivFeed:
raise RuntimeError("owner_failed")

25
tests/unit/services/domains/arxiv/test_client.py
View file

@ -1,7 +1,8 @@
from __future__ import annotations
import asyncio
from datetime import datetime, timezone
from datetime import UTC, datetime
import httpx
import pytest
from sqlalchemy.ext.asyncio import AsyncSession
@ -35,7 +36,9 @@ async def test_client_search_builds_query_and_sort_params() -> None:
captured["params"] = params
captured["request_email"] = request_email
captured["timeout_seconds"] = timeout_seconds
return httpx.Response(200, text=_CLIENT_FEED_XML, request=httpx.Request("GET", "https://export.arxiv.org/api/query"))
return httpx.Response(
200, text=_CLIENT_FEED_XML, request=httpx.Request("GET", "https://export.arxiv.org/api/query")
)
client = ArxivClient(request_fn=_request_fn)
feed = await client.search(
@ -66,7 +69,9 @@ async def test_client_lookup_ids_builds_id_list_param() -> None:
async def _request_fn(*, params, request_email, timeout_seconds):
captured["params"] = params
return httpx.Response(200, text=_CLIENT_FEED_XML, request=httpx.Request("GET", "https://export.arxiv.org/api/query"))
return httpx.Response(
200, text=_CLIENT_FEED_XML, request=httpx.Request("GET", "https://export.arxiv.org/api/query")
)
client = ArxivClient(request_fn=_request_fn)
await client.lookup_ids(id_list=["1234.5678", " 9999.0001 "], start=0, max_results=2)
@ -76,7 +81,9 @@ async def test_client_lookup_ids_builds_id_list_param() -> None:
@pytest.mark.asyncio
async def test_client_search_rejects_invalid_sort_by() -> None:
async def _unused_request_fn(*, params, request_email, timeout_seconds):
return httpx.Response(200, text=_CLIENT_FEED_XML, request=httpx.Request("GET", "https://export.arxiv.org/api/query"))
return httpx.Response(
200, text=_CLIENT_FEED_XML, request=httpx.Request("GET", "https://export.arxiv.org/api/query")
)
client = ArxivClient(request_fn=_unused_request_fn)
with pytest.raises(ArxivClientValidationError):
@ -86,7 +93,9 @@ async def test_client_search_rejects_invalid_sort_by() -> None:
@pytest.mark.asyncio
async def test_client_lookup_ids_rejects_empty_list() -> None:
async def _unused_request_fn(*, params, request_email, timeout_seconds):
return httpx.Response(200, text=_CLIENT_FEED_XML, request=httpx.Request("GET", "https://export.arxiv.org/api/query"))
return httpx.Response(
200, text=_CLIENT_FEED_XML, request=httpx.Request("GET", "https://export.arxiv.org/api/query")
)
client = ArxivClient(request_fn=_unused_request_fn)
with pytest.raises(ArxivClientValidationError):
@ -96,7 +105,9 @@ async def test_client_lookup_ids_rejects_empty_list() -> None:
@pytest.mark.asyncio
async def test_client_search_rejects_negative_start() -> None:
async def _unused_request_fn(*, params, request_email, timeout_seconds):
return httpx.Response(200, text=_CLIENT_FEED_XML, request=httpx.Request("GET", "https://export.arxiv.org/api/query"))
return httpx.Response(
200, text=_CLIENT_FEED_XML, request=httpx.Request("GET", "https://export.arxiv.org/api/query")
)
client = ArxivClient(request_fn=_unused_request_fn)
with pytest.raises(ArxivClientValidationError):
@ -172,7 +183,7 @@ async def test_request_feed_skips_live_call_when_global_cooldown_is_active(
return ArxivCooldownStatus(
is_active=True,
remaining_seconds=61.0,
cooldown_until=datetime(2026, 2, 26, 12, 1, tzinfo=timezone.utc),
cooldown_until=datetime(2026, 2, 26, 12, 1, tzinfo=UTC),
)
async def _unexpected_limit_call(*, fetch, source_path): # pragma: no cover - defensive

4
tests/unit/services/domains/arxiv/test_guards.py
View file

@ -1,6 +1,6 @@
from __future__ import annotations
from datetime import datetime, timezone
from datetime import UTC, datetime
from app.services.domains.arxiv.guards import arxiv_skip_reason_for_item
from app.services.domains.publication_identifiers.types import DisplayIdentifier
@ -25,7 +25,7 @@ def _item(
pub_url=pub_url,
pdf_url=pdf_url,
is_read=False,
first_seen_at=datetime.now(timezone.utc),
first_seen_at=datetime.now(UTC),
is_new_in_latest_run=True,
display_identifier=display_identifier,
)

4
tests/unit/services/domains/arxiv/test_parser.py
View file

@ -50,6 +50,8 @@ def test_parse_arxiv_feed_raises_on_invalid_xml() -> None:
def test_parse_arxiv_feed_raises_on_invalid_opensearch_integer() -> None:
payload = _VALID_FEED_XML.replace("<opensearch:totalResults>2</opensearch:totalResults>", "<opensearch:totalResults>x</opensearch:totalResults>")
payload = _VALID_FEED_XML.replace(
"<opensearch:totalResults>2</opensearch:totalResults>", "<opensearch:totalResults>x</opensearch:totalResults>"
)
with pytest.raises(ArxivParseError):
parse_arxiv_feed(payload)

14
tests/unit/services/domains/arxiv/test_rate_limit.py
View file

@ -1,7 +1,7 @@
from __future__ import annotations
import asyncio
from datetime import datetime, timedelta, timezone
from datetime import UTC, datetime, timedelta
import httpx
import pytest
@ -20,7 +20,7 @@ async def test_arxiv_rate_limit_respects_cooldown(db_session: AsyncSession) -> N
db_session.add(
ArxivRuntimeState(
state_key=ARXIV_RUNTIME_STATE_KEY,
cooldown_until=datetime.now(timezone.utc) + timedelta(seconds=30),
cooldown_until=datetime.now(UTC) + timedelta(seconds=30),
)
)
await db_session.commit()
@ -43,6 +43,7 @@ async def test_arxiv_rate_limit_persists_cooldown_after_429(db_session: AsyncSes
object.__setattr__(settings, "arxiv_min_interval_seconds", 0.0)
object.__setattr__(settings, "arxiv_rate_limit_cooldown_seconds", 5.0)
try:
async def _fetch() -> httpx.Response:
return httpx.Response(429, text="rate limited")
@ -57,7 +58,7 @@ async def test_arxiv_rate_limit_persists_cooldown_after_429(db_session: AsyncSes
)
state = result.scalar_one()
assert state.cooldown_until is not None
assert state.cooldown_until > datetime.now(timezone.utc)
assert state.cooldown_until > datetime.now(UTC)
@pytest.mark.asyncio
@ -120,6 +121,7 @@ async def test_arxiv_rate_limit_logs_cooldown_activation(
object.__setattr__(settings, "arxiv_min_interval_seconds", 0.0)
object.__setattr__(settings, "arxiv_rate_limit_cooldown_seconds", 5.0)
try:
async def _fetch() -> httpx.Response:
return httpx.Response(429, text="rate limited")
@ -133,9 +135,7 @@ async def test_arxiv_rate_limit_logs_cooldown_activation(
object.__setattr__(settings, "arxiv_min_interval_seconds", previous_interval)
object.__setattr__(settings, "arxiv_rate_limit_cooldown_seconds", previous_cooldown)
cooldown_events = [
entry for entry in logged_warning if entry.get("event") == "arxiv.cooldown_activated"
]
cooldown_events = [entry for entry in logged_warning if entry.get("event") == "arxiv.cooldown_activated"]
assert cooldown_events
assert cooldown_events[0]["source_path"] == "lookup_ids"
assert float(cooldown_events[0]["cooldown_remaining_seconds"]) > 0.0
@ -143,7 +143,7 @@ async def test_arxiv_rate_limit_logs_cooldown_activation(
@pytest.mark.asyncio
async def test_get_arxiv_cooldown_status_reads_active_cooldown(db_session: AsyncSession) -> None:
now_utc = datetime(2026, 2, 26, 13, 0, tzinfo=timezone.utc)
now_utc = datetime(2026, 2, 26, 13, 0, tzinfo=UTC)
existing = await db_session.get(ArxivRuntimeState, ARXIV_RUNTIME_STATE_KEY)
if existing is None:
db_session.add(

24
tests/unit/services/domains/openalex/test_client.py
View file

@ -1,6 +1,6 @@
import pytest
from app.services.domains.openalex.types import OpenAlexWork
def test_parse_openalex_work_from_api_dict() -> None:
raw_api_response = {
"id": "https://openalex.org/W2741809807",
@ -13,28 +13,19 @@ def test_parse_openalex_work_from_api_dict() -> None:
"doi": "https://doi.org/10.1038/s41586-020-0315-z",
"mag": "2741809807",
"pmid": "https://pubmed.ncbi.nlm.nih.gov/32040050",
"pmcid": "https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7325852"
},
"open_access": {
"is_oa": True,
"oa_url": "https://example.com/pdf"
"pmcid": "https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7325852",
},
"open_access": {"is_oa": True, "oa_url": "https://example.com/pdf"},
"authorships": [
{
"author_position": "first",
"author": {
"id": "https://openalex.org/A1969205032",
"display_name": "Giuseppe Carleo"
}
"author": {"id": "https://openalex.org/A1969205032", "display_name": "Giuseppe Carleo"},
},
{
"author_position": "middle",
"author": {
"id": "https://openalex.org/A4356881717",
"display_name": "Ignacio Cirac"
}
}
]
"author": {"id": "https://openalex.org/A4356881717", "display_name": "Ignacio Cirac"},
},
],
}
work = OpenAlexWork.from_api_dict(raw_api_response)
@ -52,6 +43,7 @@ def test_parse_openalex_work_from_api_dict() -> None:
assert work.authors[0].display_name == "Giuseppe Carleo"
assert work.authors[1].display_name == "Ignacio Cirac"
def test_parse_openalex_work_empty() -> None:
work = OpenAlexWork.from_api_dict({"id": "W123"})
assert work.openalex_id == "W123"

46
tests/unit/services/domains/openalex/test_matching.py
View file

@ -1,54 +1,62 @@
import pytest
from app.services.domains.openalex.types import OpenAlexWork
from app.services.domains.openalex.matching import find_best_match
from app.services.domains.openalex.types import OpenAlexWork
def test_find_best_match_exact_title():
cand1 = OpenAlexWork.from_api_dict({"id": "W1", "title": "Exact Title of the Paper"})
cand2 = OpenAlexWork.from_api_dict({"id": "W2", "title": "Totally Different Paper"})
match = find_best_match("Exact Title of the Paper", 2020, "Author A", [cand1, cand2])
assert match is not None
assert match.openalex_id == "W1"
def test_find_best_match_fuzzy_title():
# Only differences are punctuation or minor phrasing (e.g., matching a preprint title vs published)
cand1 = OpenAlexWork.from_api_dict({"id": "W1", "title": "Fuzzier Title: A Study on OpenAlex"})
cand2 = OpenAlexWork.from_api_dict({"id": "W2", "title": "Some completely unrelated work"})
match = find_best_match("Fuzzier Title A Study on OpenAlex", 2021, "Author B", [cand1, cand2])
assert match is not None
assert match.openalex_id == "W1"
def test_find_best_match_rejects_low_score():
cand1 = OpenAlexWork.from_api_dict({"id": "W1", "title": "Cats in hats"})
match = find_best_match("Dogs with logs", 2020, "Author A", [cand1])
assert match is None
def test_find_best_match_year_tiebreaker():
# Both titles are very similar, one has exact year.
cand1 = OpenAlexWork.from_api_dict({"id": "W1", "title": "The exact same title", "publication_year": 2018})
cand2 = OpenAlexWork.from_api_dict({"id": "W2", "title": "The exact same title", "publication_year": 2020})
match = find_best_match("The exact same title", 2020, "Author A", [cand1, cand2])
assert match is not None
assert match.openalex_id == "W2"
def test_find_best_match_author_tiebreaker():
# Titles and years match exactly. Author overlap decides it.
cand1 = OpenAlexWork.from_api_dict({
"id": "W1",
"title": "A popular title",
"publication_year": 2020,
"authorships": [{"author": {"display_name": "Smith, J"}}]
})
cand2 = OpenAlexWork.from_api_dict({
"id": "W2",
"title": "A popular title",
"publication_year": 2020,
"authorships": [{"author": {"display_name": "Doe, J"}}]
})
cand1 = OpenAlexWork.from_api_dict(
{
"id": "W1",
"title": "A popular title",
"publication_year": 2020,
"authorships": [{"author": {"display_name": "Smith, J"}}],
}
)
cand2 = OpenAlexWork.from_api_dict(
{
"id": "W2",
"title": "A popular title",
"publication_year": 2020,
"authorships": [{"author": {"display_name": "Doe, J"}}],
}
)
# Target authors contains "Doe"
match = find_best_match("A popular title", 2020, "A Einstein, J Doe", [cand1, cand2])
assert match is not None

12
tests/unit/services/domains/publications/test_dedup.py
View file

@ -110,12 +110,14 @@ async def test_merge_duplicate_publication_migrates_links_and_identifiers() -> N
async def test_merge_duplicate_publication_rejects_missing_publications() -> None:
session = AsyncMock()
with patch(
"app.services.domains.publications.dedup._load_publication",
new=AsyncMock(side_effect=[None, None]),
with (
patch(
"app.services.domains.publications.dedup._load_publication",
new=AsyncMock(side_effect=[None, None]),
),
pytest.raises(ValueError),
):
with pytest.raises(ValueError):
await merge_duplicate_publication(session, winner_id=1, dup_id=2)
await merge_duplicate_publication(session, winner_id=1, dup_id=2)
@pytest.mark.asyncio