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

Initial release prep

Browse source
This commit is contained in:
Justin Visser 2026-02-27 10:46:05 +01:00
parent c9b9d892f4
commit 92395b2b4b
100 changed files with 405 additions and 401 deletions
Download patch file Download diff file Expand all files Collapse all files

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

@ -9,13 +9,13 @@ from sqlalchemy import select
from sqlalchemy.ext.asyncio import AsyncSession
from app.db.models import ArxivQueryCacheEntry
from app.services.domains.arxiv.cache import (
from app.services.arxiv.cache import (
build_query_fingerprint,
get_cached_feed,
run_with_inflight_dedupe,
set_cached_feed,
)
from app.services.domains.arxiv.types import ArxivEntry, ArxivFeed, ArxivOpenSearchMeta
from app.services.arxiv.types import ArxivEntry, ArxivFeed, ArxivOpenSearchMeta
def _sample_feed(arxiv_id: str = "1234.5678") -> ArxivFeed:

12
tests/unit/services/domains/arxiv/test_client.py
View file

@ -7,10 +7,10 @@ import httpx
import pytest
from sqlalchemy.ext.asyncio import AsyncSession
from app.services.domains.arxiv import client as arxiv_client_module
from app.services.domains.arxiv.client import ArxivClient
from app.services.domains.arxiv.errors import ArxivClientValidationError, ArxivRateLimitError
from app.services.domains.arxiv.rate_limit import ArxivCooldownStatus
from app.services.arxiv import client as arxiv_client_module
from app.services.arxiv.client import ArxivClient
from app.services.arxiv.errors import ArxivClientValidationError, ArxivRateLimitError
from app.services.arxiv.rate_limit import ArxivCooldownStatus
_CLIENT_FEED_XML = """<?xml version="1.0" encoding="UTF-8"?>
<feed xmlns="http://www.w3.org/2005/Atom"
@ -160,7 +160,7 @@ async def test_client_logs_cache_hit_and_miss(
def _capture_log(_msg: str, *args, **kwargs) -> None:
logged.append({"event": _msg, **(kwargs.get("extra") or {})})
monkeypatch.setattr("app.services.domains.arxiv.client.logger.info", _capture_log)
monkeypatch.setattr("app.services.arxiv.client.logger.info", _capture_log)
client = ArxivClient(request_fn=_request_fn, cache_enabled=True)
await client.search(query="ti:test-cache")
await client.search(query="ti:test-cache")
@ -196,7 +196,7 @@ async def test_request_feed_skips_live_call_when_global_cooldown_is_active(
monkeypatch.setattr(arxiv_client_module, "get_arxiv_cooldown_status", _cooldown_status)
monkeypatch.setattr(arxiv_client_module, "run_with_global_arxiv_limit", _unexpected_limit_call)
monkeypatch.setattr("app.services.domains.arxiv.client.logger.warning", _capture_warning)
monkeypatch.setattr("app.services.arxiv.client.logger.warning", _capture_warning)
with pytest.raises(ArxivRateLimitError):
await arxiv_client_module._request_arxiv_feed(

6
tests/unit/services/domains/arxiv/test_gateway.py
View file

@ -4,9 +4,9 @@ from types import SimpleNamespace
import pytest
from app.services.domains.arxiv import application as arxiv_application
from app.services.domains.arxiv import gateway as arxiv_gateway
from app.services.domains.arxiv.types import ArxivEntry, ArxivFeed, ArxivOpenSearchMeta
from app.services.arxiv import application as arxiv_application
from app.services.arxiv import gateway as arxiv_gateway
from app.services.arxiv.types import ArxivEntry, ArxivFeed, ArxivOpenSearchMeta
from app.settings import settings

6
tests/unit/services/domains/arxiv/test_guards.py
View file

@ -2,9 +2,9 @@ from __future__ import annotations
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
from app.services.domains.publications.types import PublicationListItem
from app.services.arxiv.guards import arxiv_skip_reason_for_item
from app.services.publication_identifiers.types import DisplayIdentifier
from app.services.publications.types import PublicationListItem
def _item(

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

@ -2,8 +2,8 @@ from __future__ import annotations
import pytest
from app.services.domains.arxiv.errors import ArxivParseError
from app.services.domains.arxiv.parser import parse_arxiv_feed
from app.services.arxiv.errors import ArxivParseError
from app.services.arxiv.parser import parse_arxiv_feed
_VALID_FEED_XML = """<?xml version="1.0" encoding="UTF-8"?>
<feed xmlns="http://www.w3.org/2005/Atom"

10
tests/unit/services/domains/arxiv/test_rate_limit.py
View file

@ -9,9 +9,9 @@ from sqlalchemy import select
from sqlalchemy.ext.asyncio import AsyncSession
from app.db.models import ArxivRuntimeState
from app.services.domains.arxiv.constants import ARXIV_RUNTIME_STATE_KEY
from app.services.domains.arxiv.errors import ArxivRateLimitError
from app.services.domains.arxiv.rate_limit import get_arxiv_cooldown_status, run_with_global_arxiv_limit
from app.services.arxiv.constants import ARXIV_RUNTIME_STATE_KEY
from app.services.arxiv.errors import ArxivRateLimitError
from app.services.arxiv.rate_limit import get_arxiv_cooldown_status, run_with_global_arxiv_limit
from app.settings import settings
@ -98,7 +98,7 @@ async def test_arxiv_rate_limit_logs_request_scheduled_and_completed(
def _capture_log(_msg: str, *args, **kwargs) -> None:
logged.append({"event": _msg, **(kwargs.get("extra") or {})})
monkeypatch.setattr("app.services.domains.arxiv.rate_limit.logger.info", _capture_log)
monkeypatch.setattr("app.services.arxiv.rate_limit.logger.info", _capture_log)
await run_with_global_arxiv_limit(fetch=_fetch, source_path="search")
scheduled = [entry for entry in logged if entry.get("event") == "arxiv.request_scheduled"]
@ -128,7 +128,7 @@ async def test_arxiv_rate_limit_logs_cooldown_activation(
def _capture_warning(_msg: str, *args, **kwargs) -> None:
logged_warning.append({"event": _msg, **(kwargs.get("extra") or {})})
monkeypatch.setattr("app.services.domains.arxiv.rate_limit.logger.warning", _capture_warning)
monkeypatch.setattr("app.services.arxiv.rate_limit.logger.warning", _capture_warning)
with pytest.raises(ArxivRateLimitError):
await run_with_global_arxiv_limit(fetch=_fetch, source_path="lookup_ids")
finally:

2
tests/unit/services/domains/openalex/test_client.py
View file

@ -1,4 +1,4 @@
from app.services.domains.openalex.types import OpenAlexWork
from app.services.openalex.types import OpenAlexWork
def test_parse_openalex_work_from_api_dict() -> None:

4
tests/unit/services/domains/openalex/test_matching.py
View file

@ -1,5 +1,5 @@
from app.services.domains.openalex.matching import find_best_match
from app.services.domains.openalex.types import OpenAlexWork
from app.services.openalex.matching import find_best_match
from app.services.openalex.types import OpenAlexWork
def test_find_best_match_exact_title():

28
tests/unit/services/domains/publications/test_dedup.py
View file

@ -8,8 +8,8 @@ from unittest.mock import AsyncMock, MagicMock, patch
import pytest
from app.db.models import ScholarPublication
from app.services.domains.publications import dedup as dedup_service
from app.services.domains.publications.dedup import (
from app.services.publications import dedup as dedup_service
from app.services.publications.dedup import (
NearDuplicateCluster,
NearDuplicateMember,
find_identifier_duplicate_pairs,
@ -87,15 +87,15 @@ async def test_merge_duplicate_publication_migrates_links_and_identifiers() -> N
with (
patch(
"app.services.domains.publications.dedup._load_publication",
"app.services.publications.dedup._load_publication",
new=AsyncMock(side_effect=[winner, dup]),
),
patch(
"app.services.domains.publications.dedup._migrate_scholar_links",
"app.services.publications.dedup._migrate_scholar_links",
new=AsyncMock(),
) as mock_links,
patch(
"app.services.domains.publications.dedup._migrate_identifiers",
"app.services.publications.dedup._migrate_identifiers",
new=AsyncMock(),
) as mock_identifiers,
):
@ -112,7 +112,7 @@ async def test_merge_duplicate_publication_rejects_missing_publications() -> Non
with (
patch(
"app.services.domains.publications.dedup._load_publication",
"app.services.publications.dedup._load_publication",
new=AsyncMock(side_effect=[None, None]),
),
pytest.raises(ValueError),
@ -160,7 +160,7 @@ async def test_migrate_scholar_links_drops_conflicts() -> None:
@pytest.mark.asyncio
async def test_sweep_returns_zero_when_no_pairs() -> None:
with patch(
"app.services.domains.publications.dedup.find_identifier_duplicate_pairs",
"app.services.publications.dedup.find_identifier_duplicate_pairs",
new=AsyncMock(return_value=[]),
):
session = AsyncMock()
@ -174,11 +174,11 @@ async def test_sweep_returns_zero_when_no_pairs() -> None:
async def test_sweep_returns_merge_count() -> None:
with (
patch(
"app.services.domains.publications.dedup.find_identifier_duplicate_pairs",
"app.services.publications.dedup.find_identifier_duplicate_pairs",
new=AsyncMock(return_value=[(1, 2), (3, 4)]),
),
patch(
"app.services.domains.publications.dedup.merge_duplicate_publication",
"app.services.publications.dedup.merge_duplicate_publication",
new=AsyncMock(),
) as mock_merge,
):
@ -194,11 +194,11 @@ async def test_sweep_returns_merge_count() -> None:
async def test_sweep_merges_each_dup_only_once() -> None:
with (
patch(
"app.services.domains.publications.dedup.find_identifier_duplicate_pairs",
"app.services.publications.dedup.find_identifier_duplicate_pairs",
new=AsyncMock(return_value=[(1, 2), (1, 2)]),
),
patch(
"app.services.domains.publications.dedup.merge_duplicate_publication",
"app.services.publications.dedup.merge_duplicate_publication",
new=AsyncMock(),
) as mock_merge,
):
@ -227,7 +227,7 @@ async def test_find_near_duplicate_clusters_groups_similar_titles() -> None:
assert second is not None
with patch(
"app.services.domains.publications.dedup._load_near_duplicate_candidates",
"app.services.publications.dedup._load_near_duplicate_candidates",
new=AsyncMock(return_value=[first, second]),
):
clusters = await find_near_duplicate_clusters(AsyncMock())
@ -255,7 +255,7 @@ async def test_find_near_duplicate_clusters_skips_unrelated_titles() -> None:
assert second is not None
with patch(
"app.services.domains.publications.dedup._load_near_duplicate_candidates",
"app.services.publications.dedup._load_near_duplicate_candidates",
new=AsyncMock(return_value=[first, second]),
):
clusters = await find_near_duplicate_clusters(AsyncMock())
@ -277,7 +277,7 @@ async def test_merge_near_duplicate_cluster_merges_non_winner_members() -> None:
)
with patch(
"app.services.domains.publications.dedup.merge_duplicate_publication",
"app.services.publications.dedup.merge_duplicate_publication",
new=AsyncMock(),
) as mock_merge:
merged = await merge_near_duplicate_cluster(AsyncMock(), cluster=cluster)