cicd: add Ruff and Black (#253)

.github/workflows/github-actions.yml

@@ -3,22 +3,14 @@ on: [push, pull_request]
 jobs:
   lint:
     runs-on: ubuntu-latest
-    strategy:
-      matrix:
-        python-version: ['3.8', '3.9', '3.10', '3.11']
     steps:
       - uses: actions/checkout@v3
 
-      - name: Set up Python
-        uses: actions/setup-python@v4
-        with:
-          python-version: ${{ matrix.python-version }}
-
-      - name: Install dependencies
-        run: python3 -m pip install ".[dev]"
+      - name: black
+        uses: psf/black@stable
 
-      - name: Check style
-        run: python3 -m flake8 gene/ tests/ setup.py
+      - name: ruff
+        uses: chartboost/ruff-action@v1
 
   test:
     runs-on: ubuntu-latest

.pre-commit-config.yaml

@@ -1,10 +1,18 @@
-# See https://pre-commit.com for more information
-# See https://pre-commit.com/hooks.html for more hooks
 repos:
--   repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v1.4.0
-    hooks:
-    - id: flake8
-      additional_dependencies: [flake8-docstrings]
-    - id: check-added-large-files
-    - id: detect-private-key
+- repo: https://github.com/pre-commit/pre-commit-hooks
+  rev: v1.4.0
+  hooks:
+  - id: check-added-large-files
+  - id: detect-private-key
+  - id: trailing-whitespace
+  - id: end-of-file-fixer
+- repo: https://github.com/psf/black
+  rev: 23.7.0
+  hooks:
+    - id: black
+      language_version: python3.11
+- repo: https://github.com/astral-sh/ruff-pre-commit
+  rev: v0.0.290
+  hooks:
+    - id: ruff
+      args: [ --fix, --exit-non-zero-on-fix ]

Pipfile

@@ -9,7 +9,7 @@ fastapi = "*"
 uvicorn = "*"
 click = "*"
 boto3 = "*"
-"ga4gh.vrs" = {version = "~=2.0.0.dev0"}
+"ga4gh.vrs" = {version = "==2.0.0.dev0"}
 
 [dev-packages]
 gene = {editable = true, path = "."}
@@ -18,8 +18,8 @@ gffutils = "*"
 psycopg = {version = "*", extras=["binary"]}
 pytest = "*"
 pre-commit = "*"
-flake8 = "*"
-flake8-docstrings = "*"
+black = "*"
+ruff = "*"
 pytest-cov = "*"
 mock = "*"
 ipykernel = "*"

docs/scripts/generate_normalize_figure.py

@@ -7,8 +7,8 @@
 Embeddable HTML for the normalization figure should be deposited in the correct
 location, at docs/source/_static/html/normalize_her2.html.
 """
-from typing import Dict
 import json
+from typing import Dict
 
 import gravis as gv
 
@@ -17,17 +17,20 @@
 from gene.query import QueryHandler
 from gene.schemas import UnmergedNormalizationService
 
-
 COLORS = [
     "#F8766D",
     "#00BA38",
     "#00B9E3",
 ]
 
-GENE = 'OTX2P1'
+GENE = "OTX2P1"
 
 
 def create_gjgf(result: UnmergedNormalizationService) -> Dict:
+    """Create gravis input.
+
+    :param result: result from Unmerged Normalization search
+    """
     graph = {
         "graph": {
             "label": f"Reference Network for Search Term '{GENE}'",
@@ -37,8 +40,8 @@ def create_gjgf(result: UnmergedNormalizationService) -> Dict:
                 "arrow_size": 15,
                 "node_size": 15,
                 "node_label_size": 20,
-                "edge_size": 2
-            }
+                "edge_size": 2,
+            },
         }
     }
 
@@ -48,7 +51,7 @@ def create_gjgf(result: UnmergedNormalizationService) -> Dict:
                 "metadata": {
                     "color": COLORS[i],
                     "hover": f"{match.concept_id}\n{match.symbol}\n<i>{match.label}</i>",  # noqa: E501
-                    "click": f"<p color='black'>{json.dumps(match.model_dump(), indent=2)}</p>"  # noqa: E501
+                    "click": f"<p color='black'>{json.dumps(match.model_dump(), indent=2)}</p>",  # noqa: E501
                 }
             }
             for xref in match.xrefs:
@@ -58,8 +61,10 @@ def create_gjgf(result: UnmergedNormalizationService) -> Dict:
 
     included_edges = []
     for edge in graph["graph"]["edges"]:
-        if edge["target"] in graph["graph"]["nodes"] and \
-                edge["source"] in graph["graph"]["nodes"]:
+        if (
+            edge["target"] in graph["graph"]["nodes"]
+            and edge["source"] in graph["graph"]["nodes"]
+        ):
             included_edges.append(edge)
     graph["graph"]["edges"] = included_edges
 
@@ -75,20 +80,32 @@ def create_gjgf(result: UnmergedNormalizationService) -> Dict:
     return graph
 
 
-def gen_norm_figure():
+def gen_norm_figure() -> None:
+    """Generate normalized graph figure for docs."""
     q = QueryHandler(create_db())
     result = q.normalize_unmerged(GENE)
 
     graph = create_gjgf(result)
 
     fig = gv.d3(
-        data=graph, graph_height=200, node_hover_neighborhood=True,
-        use_links_force=True, links_force_distance=0.01, links_force_strength=0.01,
-        node_label_font="arial"
+        data=graph,
+        graph_height=200,
+        node_hover_neighborhood=True,
+        use_links_force=True,
+        links_force_distance=0.01,
+        links_force_strength=0.01,
+        node_label_font="arial",
     )
     fig.export_html(
-        (APP_ROOT.parents[0] / "docs" / "source" / "_static" / "html" / f"normalize_{GENE.lower()}.html").absolute(),  # noqa: E501
-        overwrite=True
+        (
+            APP_ROOT.parents[0]
+            / "docs"
+            / "source"
+            / "_static"
+            / "html"
+            / f"normalize_{GENE.lower()}.html"
+        ).absolute(),  # noqa: E501
+        overwrite=True,
     )
 
 

docs/source/contributing.rst

@@ -48,8 +48,7 @@ When running the web server, enable hot-reloading on new code changes: ::
 Style
 -----
 
-Code style is managed by `flake8 <https://github.com/PyCQA/flake8>`_ and should be checked via pre-commit hook before commits. Final QC is applied with GitHub Actions to every pull request.
-
+Code style is managed by `Ruff <https://github.com/astral-sh/ruff>`_ and `Black <https://github.com/psf/black>`_, and should be checked via pre-commit hook before commits. Final QC is applied with GitHub Actions to every pull request.
 
 Tests
 -----

gene/__init__.py

@@ -1,16 +1,15 @@
 """The VICC library for normalizing genes."""
-from pathlib import Path
 import logging
 from os import environ
+from pathlib import Path
 
 from .version import __version__  # noqa: F401
 
-
 APP_ROOT = Path(__file__).resolve().parents[0]
 
 logging.basicConfig(
-    filename="gene.log",
-    format="[%(asctime)s] - %(name)s - %(levelname)s : %(message)s")
+    filename="gene.log", format="[%(asctime)s] - %(name)s - %(levelname)s : %(message)s"
+)
 logger = logging.getLogger("gene")
 logger.setLevel(logging.DEBUG)
 logger.handlers = []
@@ -28,32 +27,39 @@
 )
 
 
-class DownloadException(Exception):
+class DownloadException(Exception):  # noqa: N818
     """Exception for failures relating to source file downloads."""
 
-    def __init__(self, *args, **kwargs):
-        """Initialize exception."""
-        super().__init__(*args, **kwargs)
 
+from gene.schemas import (  # noqa: E402
+    NamespacePrefix,
+    RefType,
+    SourceIDAfterNamespace,
+    SourceName,
+)
 
-from gene.schemas import SourceName, NamespacePrefix, SourceIDAfterNamespace, RefType  # noqa: E402, E501
 ITEM_TYPES = {k.lower(): v.value for k, v in RefType.__members__.items()}
 
 # Sources we import directly (HGNC, Ensembl, NCBI)
-SOURCES = {source.value.lower(): source.value
-           for source in SourceName.__members__.values()}
+SOURCES = {
+    source.value.lower(): source.value for source in SourceName.__members__.values()
+}
 
 # Set of sources we import directly
 XREF_SOURCES = {src.lower() for src in SourceName.__members__}
 
 # use to fetch source name from schema based on concept id namespace
 # e.g. {"hgnc": "HGNC"}
-PREFIX_LOOKUP = {v.value: SourceName[k].value
-                 for k, v in NamespacePrefix.__members__.items()
-                 if k in SourceName.__members__.keys()}
+PREFIX_LOOKUP = {
+    v.value: SourceName[k].value
+    for k, v in NamespacePrefix.__members__.items()
+    if k in SourceName.__members__.keys()
+}
 
 # use to generate namespace prefix from source ID value
 # e.g. {"ensg": "ensembl"}
-NAMESPACE_LOOKUP = {v.value.lower(): NamespacePrefix[k].value
-                    for k, v in SourceIDAfterNamespace.__members__.items()
-                    if v.value != ""}
+NAMESPACE_LOOKUP = {
+    v.value.lower(): NamespacePrefix[k].value
+    for k, v in SourceIDAfterNamespace.__members__.items()
+    if v.value != ""
+}