maintenance: update setup, harden code, add tests

.github/workflows/tests.yml

@@ -58,17 +58,13 @@ jobs:
       run: python -m pip install --upgrade -e ".[dev]"
 
     # tests
-    - name: Lint with flake8
-      run: |
-        # stop the build if there are Python syntax errors or undefined names
-        flake8 . --count --select=E9,F63,F7,F82 --show-source --statistics
-        # exit-zero treats all errors as warnings. The GitHub editor is 127 chars wide
-        flake8 . --count --exit-zero --max-complexity=10 --max-line-length=127 --statistics
+    - name: Lint with ruff
+      run: ruff check .
 
     - name: Code format and type checking
       if: ${{ matrix.python-version == env.REF_PY_VERSION }}
       run: |
-        black --check --diff htmldate
+        ruff format --check htmldate
         mypy -p htmldate
 
     - name: Install full dependencies

CONTRIBUTING.md

@@ -25,8 +25,7 @@ and if there are no errors.
 2. Run the tests and code quality tools:
    - Tests with `pytest`
    - Type checking with `mypy` on the directory: `mypy htmldate/`
-   - Code formatting with `black` on the directory as well
-   - Optional: install `pre-commit` to use the corresponding commit hooks
+   - Linting with `ruff check .` and formatting with `ruff format htmldate/`
 
 
 For further questions you can use [GitHub issues](https://github.com/adbar/htmldate/issues) or [E-Mail](https://adrien.barbaresi.eu/).

docs/index.rst

@@ -21,9 +21,9 @@ Htmldate: Find the Publication Date of Web Pages
    :target: https://doi.org/10.21105/joss.02439
    :alt: JOSS article reference DOI: 10.21105/joss.02439
 
-.. image:: https://img.shields.io/badge/code%20style-black-000000.svg
-   :target: https://github.com/psf/black
-   :alt: Code style: black
+.. image:: https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/astral-sh/ruff/main/assets/badge/v2.json
+   :target: https://github.com/astral-sh/ruff
+   :alt: Ruff
 
 |
 

htmldate/cli.py

@@ -7,7 +7,6 @@
 import sys
 
 from platform import python_version
-from typing import Any, Optional, Union
 
 from lxml.html import HtmlElement
 
@@ -17,12 +16,12 @@
 
 
 def cli_examine(
-    htmlstring: Union[str, HtmlElement],
-    args: Any,
-) -> Optional[str]:
+    htmlstring: str | HtmlElement | None,
+    args: argparse.Namespace,
+) -> str | None:
     """Generic safeguards and triggers"""
     # safety check
-    if is_wrong_document(htmlstring):
+    if htmlstring is None or is_wrong_document(htmlstring):
         sys.stderr.write("# ERROR: document is empty or too large\n")
         return None
     return find_date(
@@ -35,7 +34,7 @@ def cli_examine(
     )
 
 
-def parse_args(args: Any) -> Any:
+def parse_args(args: list[str]) -> argparse.Namespace:
     """Define parser for command-line arguments"""
     argsparser = argparse.ArgumentParser()
     argsparser.add_argument(
@@ -67,10 +66,10 @@ def parse_args(args: Any) -> Any:
         action="version",
         version=f"Htmldate {__version__} - Python {python_version()}",
     )
-    return argsparser.parse_args()
+    return argsparser.parse_args(args)
 
 
-def process_args(args: Any) -> None:
+def process_args(args: argparse.Namespace) -> None:
     """Process the arguments passed on the command-line."""
     # verbosity
     if args.verbose:
@@ -98,7 +97,7 @@ def process_args(args: Any) -> None:
         with open(args.inputfile, mode="r", encoding="utf-8") as inputfile:
             for line in inputfile:
                 htmltext = fetch_url(line.strip())
-                result = cli_examine(htmltext, args)  # type: ignore[arg-type]
+                result = cli_examine(htmltext, args)
                 sys.stdout.write(f"{line.strip()}\t{result or 'None'}\n")