Start applying ruff (#1371)

Start applying ruff, to replace black

notebooks/Bioregistry Taxonomy Curation via Wikidata.ipynb

@@ -9,13 +9,14 @@
    "source": [
     "# Get wikidata taxonomy properties\n",
     "\n",
-    "import bioregistry\n",
-    "import bioregistry.version\n",
-    "import requests\n",
     "import pandas as pd\n",
-    "from bioregistry.utils import norm, query_wikidata\n",
+    "import requests\n",
     "from bs4 import BeautifulSoup\n",
     "\n",
+    "import bioregistry\n",
+    "import bioregistry.version\n",
+    "from bioregistry.utils import query_wikidata\n",
+    "\n",
     "pd.set_option(\"display.max_rows\", None)"
    ]
   },

notebooks/Preparing the GO Annotation Database for Integration.ipynb

@@ -107,9 +107,10 @@
     }
    ],
    "source": [
-    "import bioregistry.pandas as brpd\n",
     "import pandas as pd\n",
     "\n",
+    "import bioregistry.pandas as brpd\n",
+    "\n",
     "# Focus on these columns when displaying the data\n",
     "columns = [0, 1, 4, 5, 7, 12]\n",
     "\n",

setup.cfg

@@ -29,7 +29,9 @@ exclude =
     .eggs,
     data
 per-file-ignores =
-    src/bioregistry/app/api.py:B008
+    src/bioregistry/app/api.py:B008,DAR101,DAR201
+    src/bioregistry/app/ui.py:DAR101,DAR201
+    src/bioregistry/app/app.py:DAR101,DAR201
 max-line-length = 120
 max-complexity = 20
 import-order-style = pycharm

src/bioregistry/__init__.py

@@ -1,5 +1,3 @@
-# -*- coding: utf-8 -*-
-
 """Extract registry information."""
 
 from .collection_api import get_collection, get_context  # noqa:F401

src/bioregistry/__main__.py

@@ -1,5 +1,3 @@
-# -*- coding: utf-8 -*-
-
 """Command line interface for the bioregistry."""
 
 from .cli import main  # type:ignore

src/bioregistry/analysis/__init__.py

@@ -1,3 +1 @@
-# -*- coding: utf-8 -*-
-
 """Analyses build on the Bioregistry."""

src/bioregistry/analysis/paper_ranking.py

@@ -26,7 +26,7 @@
 from collections import defaultdict
 from collections.abc import Iterable
 from pathlib import Path
-from typing import Any, NamedTuple, Optional, Union
+from typing import Any, NamedTuple, Union
 
 import click
 import numpy as np
@@ -55,7 +55,10 @@
 DIRECTORY = ROOT.joinpath("exports", "analyses", "paper_ranking")
 DIRECTORY.mkdir(exist_ok=True, parents=True)
 
-URL = "https://docs.google.com/spreadsheets/d/e/2PACX-1vRPtP-tcXSx8zvhCuX6fqz_QvHowyAoDahnkixARk9rFTe0gfBN9GfdG6qTNQHHVL0i33XGSp_nV9XM/pub?output=csv"
+URL = (
+    "https://docs.google.com/spreadsheets/d/e/2PACX-1vRPtP-tcXSx8zvhCuX6fqz_QvHowyAoDahnk"
+    "ixARk9rFTe0gfBN9GfdG6qTNQHHVL0i33XGSp_nV9XM/pub?output=csv"
+)
 
 XTrain: TypeAlias = NDArray[np.float64]
 YTrain: TypeAlias = NDArray[np.float64]
@@ -74,7 +77,7 @@
 ]
 
 
-def get_publications_from_bioregistry(path: Optional[Path] = None) -> pd.DataFrame:
+def get_publications_from_bioregistry(path: Path | None = None) -> pd.DataFrame:
     """Load bioregistry data from a JSON file, extracting publication details and fetching abstracts if missing.
 
     :param path: Path to the bioregistry JSON file.
@@ -129,7 +132,7 @@ def load_curated_papers(file_path: Path = CURATED_PAPERS_PATH) -> pd.DataFrame:
     return curated_df
 
 
-def _get_metadata_for_ids(pubmed_ids: Iterable[Union[int, str]]) -> dict[str, dict[str, Any]]:
+def _get_metadata_for_ids(pubmed_ids: Iterable[int | str]) -> dict[str, dict[str, Any]]:
     """Get metadata for articles in PubMed, wrapping the INDRA client."""
     from indra.literature import pubmed_client
 
@@ -225,7 +228,7 @@ def load_google_curation_df() -> pd.DataFrame:
     return df
 
 
-def _map_labels(s: str) -> Optional[int]:
+def _map_labels(s: str) -> int | None:
     """Map labels to binary values.
 
     :param s: Label value.
@@ -267,6 +270,7 @@ def generate_meta_features(
     :param classifiers: List of trained classifiers.
     :param x_train: Training features.
     :param y_train: Training labels.
+    :param cv: Number of folds for cross-validation
     :return: DataFrame containing meta-features.
     """
     df = pd.DataFrame()

src/bioregistry/app/__init__.py

@@ -1,3 +1 @@
-# -*- coding: utf-8 -*-
-
 """Web application for the Bioregistry."""

src/bioregistry/app/api.py

@@ -1,10 +1,9 @@
-# -*- coding: utf-8 -*-
-
 """FastAPI blueprint and routes."""
 
 from __future__ import annotations
 
-from typing import Any, List, Mapping, Optional, Set
+from collections.abc import Mapping
+from typing import Any
 
 import yaml
 from curies import Reference
@@ -84,7 +83,7 @@ def render(self, content: Any) -> bytes:
 }
 
 
-def _handle_formats(accept: Optional[str], fmt: Optional[str]) -> str:
+def _handle_formats(accept: str | None, fmt: str | None) -> str:
     if fmt:
         if fmt not in FORMAT_MAP:
             raise HTTPException(
@@ -104,8 +103,8 @@ def _handle_formats(accept: Optional[str], fmt: Optional[str]) -> str:
 @api_router.get("/registry", response_model=Mapping[str, Resource], tags=["resource"])
 def get_resources(
     request: Request,
-    accept: Optional[str] = ACCEPT_HEADER,
-    format: Optional[str] = FORMAT_QUERY,
+    accept: str | None = ACCEPT_HEADER,
+    format: str | None = FORMAT_QUERY,
 ):
     """Get all resources."""
     accept = _handle_formats(accept, format)
@@ -169,8 +168,8 @@ def get_resource(
 )
 def get_metaresources(
     request: Request,
-    accept: Optional[str] = ACCEPT_HEADER,
-    format: Optional[str] = FORMAT_QUERY,
+    accept: str | None = ACCEPT_HEADER,
+    format: str | None = FORMAT_QUERY,
 ):
     """Get all registries."""
     accept = _handle_formats(accept, format)
@@ -262,8 +261,8 @@ class MappingResponseMeta(BaseModel):
     target: str
     len_source_only: int
     len_target_only: int
-    source_only: List[str]
-    target_only: List[str]
+    source_only: list[str]
+    target_only: list[str]
 
 
 class MappingResponse(BaseModel):
@@ -320,8 +319,8 @@ def get_metaresource_mappings(request: Request, metaprefix: str = METAPREFIX_PAT
 @api_router.get("/collection", response_model=Mapping[str, Collection], tags=["collection"])
 def get_collections(
     request: Request,
-    accept: Optional[str] = ACCEPT_HEADER,
-    format: Optional[str] = FORMAT_QUERY,
+    accept: str | None = ACCEPT_HEADER,
+    format: str | None = FORMAT_QUERY,
 ):
     """Get all collections."""
     accept = _handle_formats(accept, format)
@@ -357,8 +356,8 @@ def get_collection(
         description="The 7-digit collection identifier",
         examples=["0000001"],
     ),
-    accept: Optional[str] = ACCEPT_HEADER,
-    format: Optional[str] = FORMAT_QUERY,
+    accept: str | None = ACCEPT_HEADER,
+    format: str | None = FORMAT_QUERY,
 ):
     """Get a collection."""
     manager = request.app.manager
@@ -388,8 +387,8 @@ def get_collection(
 @api_router.get("/context", response_model=Mapping[str, Context], tags=["context"])
 def get_contexts(
     request: Request,
-    accept: Optional[str] = ACCEPT_HEADER,
-    format: Optional[str] = FORMAT_QUERY,
+    accept: str | None = ACCEPT_HEADER,
+    format: str | None = FORMAT_QUERY,
 ):
     """Get all context."""
     accept = _handle_formats(accept, format)
@@ -416,8 +415,8 @@ def get_context(
 @api_router.get("/contributors", response_model=Mapping[str, Attributable], tags=["contributor"])
 def get_contributors(
     request: Request,
-    accept: Optional[str] = ACCEPT_HEADER,
-    format: Optional[str] = FORMAT_QUERY,
+    accept: str | None = ACCEPT_HEADER,
+    format: str | None = FORMAT_QUERY,
 ):
     """Get all context."""
     contributors = request.app.manager.read_contributors()
@@ -434,11 +433,11 @@ class ContributorResponse(BaseModel):
     """A response with information about a contributor."""
 
     contributor: Attributable
-    prefix_contributions: Set[str]
-    prefix_reviews: Set[str]
-    prefix_contacts: Set[str]
-    registries: Set[str]
-    collections: Set[str]
+    prefix_contributions: set[str]
+    prefix_reviews: set[str]
+    prefix_contacts: set[str]
+    registries: set[str]
+    collections: set[str]
 
 
 @api_router.get("/contributor/{orcid}", response_model=ContributorResponse, tags=["contributor"])
@@ -547,7 +546,7 @@ def post_parse_uri(
 @api_router.get("/context.jsonld", tags=["resource"])
 def generate_context_json_ld(
     request: Request,
-    prefix: List[str] = Query(description="The prefix for the entry. Can be given multiple."),
+    prefix: list[str] = Query(description="The prefix for the entry. Can be given multiple."),
 ):
     """Generate an *ad-hoc* context JSON-LD file from the given parameters.
 
@@ -558,7 +557,7 @@ def generate_context_json_ld(
     or you can use multiple entries for "prefix" like:
 
     https://bioregistry.io/api/context.jsonld?prefix=go&prefix=doid&prefix=oa
-    """  # noqa:DAR101,DAR201
+    """
     manager = request.app.manager
     prefix_map = {}
     for value in prefix:

src/bioregistry/app/cli.py

@@ -1,5 +1,3 @@
-# -*- coding: utf-8 -*-
-
 """Web command for running the app."""
 
 from pathlib import Path

src/bioregistry/app/constants.py

@@ -1,5 +1,3 @@
-# -*- coding: utf-8 -*
-
 """Large data chunks for the web app."""
 
 from bioregistry import version

src/bioregistry/app/impl.py

@@ -1,9 +1,10 @@
 """App builder interface."""
 
 import json
+from collections.abc import Mapping
 from pathlib import Path
 from textwrap import dedent
-from typing import TYPE_CHECKING, Any, Mapping, Optional, Union
+from typing import TYPE_CHECKING, Any, Optional, Union
 
 from a2wsgi import WSGIMiddleware
 from curies.mapping_service import MappingServiceGraph, MappingServiceSPARQLProcessor

src/bioregistry/app/test.py

@@ -1,5 +1,3 @@
-# -*- coding: utf-8 -*-
-
 """Test the resolution API."""
 
 import sys

src/bioregistry/app/ui.py

@@ -1,5 +1,3 @@
-# -*- coding: utf-8 -*-
-
 """User blueprint for the bioregistry web application."""
 
 from __future__ import annotations
@@ -11,7 +9,6 @@
 from collections import defaultdict
 from operator import attrgetter
 from pathlib import Path
-from typing import Optional
 
 import flask
 import werkzeug
@@ -137,15 +134,15 @@ def resource(prefix: str) -> str | flask.Response:
         example_curie=example_curie,
         example_curie_extras=example_curie_extras,
         mappings=[
-            dict(
-                metaprefix=metaprefix,
-                metaresource=manager.get_registry(metaprefix),
-                xref=xref,
-                homepage=manager.get_registry_homepage(metaprefix),
-                name=manager.get_registry_name(metaprefix),
-                short_name=manager.get_registry_short_name(metaprefix),
-                uri=manager.get_registry_provider_uri_format(metaprefix, xref),
-            )
+            {
+                "metaprefix": metaprefix,
+                "metaresource": manager.get_registry(metaprefix),
+                "xref": xref,
+                "homepage": manager.get_registry_homepage(metaprefix),
+                "name": manager.get_registry_name(metaprefix),
+                "short_name": manager.get_registry_short_name(metaprefix),
+                "uri": manager.get_registry_provider_uri_format(metaprefix, xref),
+            }
             for metaprefix, xref in _resource.get_mappings().items()
         ],
         synonyms=_resource.get_synonyms(),
@@ -194,7 +191,7 @@ def metaresource(metaprefix: str) -> str | flask.Response:
         return serialize_model(entry, metaresource_to_rdf_str, negotiate=True)
 
     external_prefix = entry.example
-    bioregistry_prefix: Optional[str]
+    bioregistry_prefix: str | None
     if metaprefix == "bioregistry":
         bioregistry_prefix = external_prefix
     else:
@@ -309,7 +306,7 @@ def get_value(self):
         return self.response
 
 
-def _clean_reference(prefix: str, identifier: Optional[str] = None):
+def _clean_reference(prefix: str, identifier: str | None = None):
     if ":" in prefix:
         # A colon might appear in the prefix if there are multiple colons
         # in the CURIE, since Flask/Werkzeug parses from right to left.
@@ -375,7 +372,7 @@ def reference(prefix: str, identifier: str) -> str:
 @ui_blueprint.route("/<prefix>:<path:identifier>")
 @ark_hacked_route
 def resolve(
-    prefix: str, identifier: Optional[str] = None
+    prefix: str, identifier: str | None = None
 ) -> str | werkzeug.Response | tuple[str, int]:
     """Resolve a CURIE.
 
@@ -384,7 +381,7 @@ def resolve(
     1. The prefix is not registered
     2. The prefix has a validation pattern and the identifier does not match it
     3. There are no providers available for the URL
-    """  # noqa:DAR101,DAR201
+    """
     try:
         _resource, identifier = _clean_reference(prefix, identifier)
     except ResponseWrapper as rw:
@@ -420,14 +417,14 @@ def resolve(
 
 @ui_blueprint.route("/metaregistry/<metaprefix>/<metaidentifier>")
 @ui_blueprint.route("/metaregistry/<metaprefix>/<metaidentifier>:<path:identifier>")
-def metaresolve(metaprefix: str, metaidentifier: str, identifier: Optional[str] = None):
+def metaresolve(metaprefix: str, metaidentifier: str, identifier: str | None = None):
     """Redirect to a prefix page or meta-resolve the CURIE.
 
     Test this function locally with:
 
     - http://localhost:5000/metaregistry/obofoundry/GO
     - http://localhost:5000/metaregistry/obofoundry/GO:0032571
-    """  # noqa:DAR101,DAR201
+    """
     if metaprefix not in manager.metaregistry:
         return abort(404, f"invalid metaprefix: {metaprefix}")
     prefix = manager.lookup_from(metaprefix, metaidentifier, normalize=True)