Add linting and formatting

.github/workflows/lint.yml

@@ -0,0 +1,19 @@
+name: Lint
+
+on: [push, pull_request, workflow_dispatch]
+
+env:
+  FORCE_COLOR: 1
+
+jobs:
+  lint:
+    runs-on: ubuntu-latest
+
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          persist-credentials: false
+      - uses: actions/setup-python@v5
+        with:
+          python-version: "3.x"
+      - uses: tox-dev/action-pre-commit-uv@v1

.github/workflows/update.yml

@@ -15,7 +15,7 @@ jobs:
       - uses: actions/setup-python@v5
         with:
           python-version: "3.x"
-      - uses: astral-sh/setup-uv@v4
+      - uses: astral-sh/setup-uv@v5
       - uses: actions/checkout@v4
       - run: sudo apt-get install -y gettext
       - run: uv run generate.py  # generates "index.html"

.pre-commit-config.yaml

@@ -0,0 +1,41 @@
+repos:
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.8.4
+    hooks:
+      - id: ruff
+        args: [--exit-non-zero-on-fix]
+
+  - repo: https://github.com/psf/black-pre-commit-mirror
+    rev: 24.10.0
+    hooks:
+      - id: black
+
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v5.0.0
+    hooks:
+      - id: check-added-large-files
+      - id: check-case-conflict
+      - id: check-merge-conflict
+      - id: check-yaml
+      - id: debug-statements
+      - id: end-of-file-fixer
+      - id: forbid-submodules
+      - id: trailing-whitespace
+
+  - repo: https://github.com/python-jsonschema/check-jsonschema
+    rev: 0.30.0
+    hooks:
+      - id: check-github-workflows
+
+  - repo: https://github.com/rhysd/actionlint
+    rev: v1.7.5
+    hooks:
+      - id: actionlint
+
+  - repo: meta
+    hooks:
+      - id: check-hooks-apply
+      - id: check-useless-excludes
+
+ci:
+  autoupdate_schedule: quarterly

completion.py

@@ -11,7 +11,7 @@
 
 @cache
 def branches_from_devguide(devguide_dir: Path) -> list[str]:
-    p = devguide_dir.joinpath('include/release-cycle.json')
+    p = devguide_dir.joinpath("include/release-cycle.json")
     data = json.loads(p.read_text())
     return [
         branch for branch in data if data[branch]["status"] in ("bugfix", "security")
@@ -20,18 +20,24 @@ def branches_from_devguide(devguide_dir: Path) -> list[str]:
 
 def get_completion(clones_dir: str, repo: str) -> tuple[float, int]:
     clone_path = Path(clones_dir, repo)
-    for branch in branches_from_devguide(Path(clones_dir, 'devguide')) + ['master']:
+    for branch in branches_from_devguide(Path(clones_dir, "devguide")) + ["master"]:
         try:
-            git.Repo.clone_from(f'https://github.com/{repo}.git', clone_path, branch=branch)
+            git.Repo.clone_from(
+                f"https://github.com/{repo}.git", clone_path, branch=branch
+            )
         except git.GitCommandError:
-            print(f'failed to clone {repo} {branch}')
+            print(f"failed to clone {repo} {branch}")
             translators_number = 0
             continue
         else:
             translators_number = translators.get_number(clone_path)
             break
     with TemporaryDirectory() as tmpdir:
         completion = potodo.merge_and_scan_path(
-            clone_path, pot_path=Path(clones_dir, 'cpython/Doc/build/gettext'), merge_path=Path(tmpdir), hide_reserved=False, api_url=''
+            clone_path,
+            pot_path=Path(clones_dir, "cpython/Doc/build/gettext"),
+            merge_path=Path(tmpdir),
+            hide_reserved=False,
+            api_url="",
         ).completion
     return completion, translators_number

generate.py

@@ -25,13 +25,22 @@
 generation_time = datetime.now(timezone.utc)
 
 with TemporaryDirectory() as clones_dir:
-    Repo.clone_from(f'https://github.com/python/devguide.git', devguide_dir := Path(clones_dir, 'devguide'), depth=1)
+    Repo.clone_from(
+        "https://github.com/python/devguide.git",
+        devguide_dir := Path(clones_dir, "devguide"),
+        depth=1,
+    )
     latest_branch = branches_from_devguide(devguide_dir)[0]
     Repo.clone_from(
-        f'https://github.com/python/cpython.git', Path(clones_dir, 'cpython'), depth=1, branch=latest_branch
+        "https://github.com/python/cpython.git",
+        Path(clones_dir, "cpython"),
+        depth=1,
+        branch=latest_branch,
+    )
+    subprocess.run(["make", "-C", Path(clones_dir, "cpython/Doc"), "venv"], check=True)
+    subprocess.run(
+        ["make", "-C", Path(clones_dir, "cpython/Doc"), "gettext"], check=True
     )
-    subprocess.run(['make', '-C', Path(clones_dir, 'cpython/Doc'), 'venv'], check=True)
-    subprocess.run(['make', '-C', Path(clones_dir, 'cpython/Doc'), 'gettext'], check=True)
     switcher_languages = list(switcher.get_languages())
     for language, repo in repositories.get_languages_and_repos(devguide_dir):
         if repo:
@@ -78,7 +87,7 @@
     <a href="https://github.com/{{ repo }}" target="_blank">
       {{ language }}
     </a>
-  </td>  
+  </td>
   <td data-label="build">
     {% if in_switcher %}
       <a href="https://docs.python.org/{{ language }}/">in switcher</a>
@@ -111,7 +120,9 @@
 """
 )
 
-output = template.render(completion_progress=completion_progress, generation_time=generation_time)
+output = template.render(
+    completion_progress=completion_progress, generation_time=generation_time
+)
 
 with open("index.html", "w") as file:
     file.write(output)

repositories.py

@@ -1,4 +1,3 @@
-import tempfile
 import pathlib
 import re
 from typing import Generator, Optional
@@ -7,14 +6,18 @@
 from docutils.nodes import table, row
 
 
-def get_languages_and_repos(devguide_dir: pathlib.Path) -> Generator[tuple[str, Optional[str]], None, None]:
-    translating = devguide_dir.joinpath('documentation/translating.rst').read_text()
+def get_languages_and_repos(
+    devguide_dir: pathlib.Path,
+) -> Generator[tuple[str, Optional[str]], None, None]:
+    translating = devguide_dir.joinpath("documentation/translating.rst").read_text()
     doctree = core.publish_doctree(translating)
 
     for node in doctree.traverse(table):
         for row_node in node.traverse(row)[1:]:
             language = row_node[0].astext()
             repo = row_node[2].astext()
-            language_code = re.match(r'.* \((.*)\)', language).group(1).lower().replace('_', '-')
-            repo_match = re.match(':github:`GitHub <(.*)>`', repo)
+            language_code = (
+                re.match(r".* \((.*)\)", language).group(1).lower().replace("_", "-")
+            )
+            repo_match = re.match(":github:`GitHub <(.*)>`", repo)
             yield language_code, repo_match and repo_match.group(1)

switcher.py

@@ -6,7 +6,6 @@
 """
 
 import tomllib
-from collections import defaultdict
 from typing import Generator
 
 import requests

translators.py

@@ -10,20 +10,22 @@ def get_number(path: Path) -> int:
     from_git_history = get_number_from_git_history(path)
     return max(from_headers, from_git_history)
 
+
 def get_number_from_git_history(path: Path) -> int:
-    return len(Repo(path).git.shortlog('-s', 'HEAD').splitlines())
+    return len(Repo(path).git.shortlog("-s", "HEAD").splitlines())
+
 
 def yield_from_headers(path: Path) -> Generator[str, None, None]:
-    for file in path.rglob('*.po'):
+    for file in path.rglob("*.po"):
         try:
             header = pofile(file).header.splitlines()
         except IOError:
             continue
-        if 'Translators:' not in header:
+        if "Translators:" not in header:
             continue
-        for translator_record in header[header.index('Translators:') + 1:]:
+        for translator_record in header[header.index("Translators:") + 1 :]:
             try:
-                translator, _year = translator_record.split(', ')
+                translator, _year = translator_record.split(", ")
             except ValueError:
                 yield translator_record
             else:

visitors.py

@@ -7,8 +7,12 @@
 
 
 def get_number_of_visitors(language: str) -> int:
-    param = urllib.parse.urlencode({'filters': f'[["contains","event:page",["/{language}/"]]]'})
-    r = requests.get(f'https://plausible.io/docs.python.org/export?{param}', timeout=10)
-    with zipfile.ZipFile(io.BytesIO(r.content), 'r') as z, z.open('visitors.csv') as csv_file:
+    param = urllib.parse.urlencode(
+        {"filters": f'[["contains","event:page",["/{language}/"]]]'}
+    )
+    r = requests.get(f"https://plausible.io/docs.python.org/export?{param}", timeout=10)
+    with zipfile.ZipFile(io.BytesIO(r.content), "r") as z, z.open(
+        "visitors.csv"
+    ) as csv_file:
         csv_reader = csv.DictReader(io.TextIOWrapper(csv_file))
         return sum(int(row["visitors"]) for row in csv_reader)