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

18
app/services/domains/publications/dedup.py
View file

@ -1,9 +1,9 @@
from __future__ import annotations
from dataclasses import dataclass
import hashlib
import logging
from typing import Iterable
from collections.abc import Iterable
from dataclasses import dataclass
from sqlalchemy import delete, select
from sqlalchemy.ext.asyncio import AsyncSession
@ -113,9 +113,7 @@ async def _load_publication(
*,
publication_id: int,
) -> Publication | None:
result = await db_session.execute(
select(Publication).where(Publication.id == publication_id)
)
result = await db_session.execute(select(Publication).where(Publication.id == publication_id))
return result.scalar_one_or_none()
@ -160,9 +158,7 @@ async def _migrate_scholar_links(
dup_links = dup_links_result.scalars().all()
winner_profiles_result = await db_session.execute(
select(ScholarPublication.scholar_profile_id).where(
ScholarPublication.publication_id == winner_id
)
select(ScholarPublication.scholar_profile_id).where(ScholarPublication.publication_id == winner_id)
)
winner_profiles: set[int] = {row for (row,) in winner_profiles_result}
@ -346,11 +342,7 @@ def _candidate_from_row(
def _normalized_tokens(tokens: Iterable[str]) -> set[str]:
return {
token
for token in tokens
if len(token) >= NEAR_DUP_MIN_TOKEN_LENGTH and token not in NEAR_DUP_STOPWORDS
}
return {token for token in tokens if len(token) >= NEAR_DUP_MIN_TOKEN_LENGTH and token not in NEAR_DUP_STOPWORDS}
def _cluster_candidate_groups(