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

22
app/services/domains/publications/pdf_resolution_pipeline.py
View file

@ -1,15 +1,15 @@
from __future__ import annotations
from dataclasses import dataclass
import logging
from dataclasses import dataclass
from typing import Any
from app.logging_utils import structured_log
from app.services.domains.arxiv.application import ArxivRateLimitError
from app.services.domains.arxiv.guards import arxiv_skip_reason_for_item
from app.services.domains.openalex.client import OpenAlexBudgetExhaustedError
from app.services.domains.publications.types import PublicationListItem
from app.services.domains.unpaywall.application import OaResolutionOutcome, resolve_publication_oa_outcomes
from app.logging_utils import structured_log
from app.settings import settings
logger = logging.getLogger(__name__)
@ -66,6 +66,7 @@ async def _openalex_outcome(
return None
import re
safe_title = re.sub(r"[^\w\s]", " ", row.title)
safe_title = " ".join(safe_title.split())
if not safe_title:
@ -107,12 +108,24 @@ async def _arxiv_outcome(
from app.services.domains.arxiv.application import discover_arxiv_id_for_publication
if not allow_lookup:
structured_log(logger, "info", "pdf_resolution.arxiv_skipped", publication_id=int(row.publication_id), skip_reason="batch_arxiv_cooldown_active")
structured_log(
logger,
"info",
"pdf_resolution.arxiv_skipped",
publication_id=int(row.publication_id),
skip_reason="batch_arxiv_cooldown_active",
)
return None
skip_reason = arxiv_skip_reason_for_item(item=row)
if skip_reason is not None:
structured_log(logger, "info", "pdf_resolution.arxiv_skipped", publication_id=int(row.publication_id), skip_reason=skip_reason)
structured_log(
logger,
"info",
"pdf_resolution.arxiv_skipped",
publication_id=int(row.publication_id),
skip_reason=skip_reason,
)
return None
try:
@ -134,7 +147,6 @@ async def _arxiv_outcome(
return None
async def _oa_outcome(
*,
row: PublicationListItem,