setup: use pyproject.toml file and update test workflow (#160)

* setup: use pyproject.toml file * update workflow * simplify workflow * review order * remove condition
adbar · Aug 26, 2024 · 3c86189 · 3c86189
1 parent dbcc2eb
commit 3c86189
Show file tree

Hide file tree

Showing 3 changed files with 106 additions and 107 deletions.
diff --git a/.github/workflows/tests.yml b/.github/workflows/tests.yml
@@ -68,25 +68,20 @@ jobs:
         # 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: Code format with black
+    - name: Code format and type checking
       if: ${{ matrix.python-version == '3.11' }}
       run: |
-        python -m pip install --upgrade black
+        python -m pip install --upgrade .[dev]
         black --check --diff htmldate
+        mypy -p htmldate
 
-    - name: Install dependencies
+    - name: Install minimal dependencies
       run: python -m pip install -e "."
 
     - name: Install full dependencies
       if: ${{ matrix.env.MINIMAL == 'false'}}
       run: python -m pip install -e ".[all]"
 
-    - name: Type checking with mypy
-      if: ${{ matrix.python-version == '3.11' }}
-      run: |
-        python -m pip install --upgrade mypy types-dateparser types-python-dateutil types-lxml types-urllib3
-        mypy -p htmldate
-
     - name: Test with pytest
       run: |
         python -m pip install --upgrade pytest pytest-cov

diff --git a/pyproject.toml b/pyproject.toml
@@ -0,0 +1,100 @@
+# https://pip.pypa.io/en/stable/reference/build-system/pyproject-toml/
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "htmldate"
+description = "Fast and robust extraction of original and updated publication dates from URLs and web pages."
+readme = "README.md"
+license = { text = "Apache 2.0" }
+dynamic = ["version"]
+requires-python = ">=3.8"
+authors = [
+  {name = "Adrien Barbaresi", email = "barbaresi@bbaw.de"}
+]
+keywords=[
+    "datetime",
+    "date-parser",
+    "entity-extraction",
+    "html-extraction",
+    "html-parsing",
+    "metadata-extraction",
+    "webarchives",
+    "web-scraping",
+]
+classifiers = [
+    # http://pypi.python.org/pypi?%3Aaction=list_classifiers
+    "Development Status :: 5 - Production/Stable",
+    "Environment :: Console",
+    "Intended Audience :: Developers",
+    "Intended Audience :: Education",
+    "Intended Audience :: Information Technology",
+    "Intended Audience :: Science/Research",
+    "License :: OSI Approved :: Apache Software License",
+    "Operating System :: MacOS :: MacOS X",
+    "Operating System :: Microsoft :: Windows",
+    "Operating System :: POSIX :: Linux",
+    "Programming Language :: Python",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.8",
+    "Programming Language :: Python :: 3.9",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "Topic :: Internet :: WWW/HTTP",
+    "Topic :: Scientific/Engineering :: Information Analysis",
+    "Topic :: Text Processing :: Linguistic",
+    "Topic :: Text Processing :: Markup :: HTML",
+]
+dependencies = [
+    "charset_normalizer >= 3.3.2",
+    "dateparser >= 1.1.2",  # 1.1.3+ slower
+    # see tests on Github Actions
+    "lxml == 4.9.2 ; platform_system == 'Darwin' and python_version <= '3.8'",
+    "lxml >= 5.2.2, < 6 ; platform_system != 'Darwin' or python_version > '3.8'",
+    "python-dateutil >= 2.8.2",
+    "urllib3 >= 1.26, < 3",
+]
+
+# https://setuptools.pypa.io/en/latest/userguide/pyproject_config.html
+[tool.setuptools]
+packages = ["htmldate"]
+
+# https://packaging.python.org/en/latest/guides/single-sourcing-package-version/
+[tool.setuptools.dynamic]
+version = {attr = "htmldate.__version__"}
+
+[project.scripts]
+htmldate = "htmldate.cli:main"
+
+[project.urls]
+"Homepage" = "https://htmldate.readthedocs.io"
+"Source" = "https://github.com/adbar/htmldate"
+"Blog" = "https://adrien.barbaresi.eu/blog/"  # /tag/htmldate.html
+"Tracker" = "https://github.com/adbar/htmldate/issues"
+
+# Development extras
+[project.optional-dependencies]
+dev = [
+    "black",
+    "mypy",
+    "pytest",
+    "pytest-cov",
+    "types-dateparser",
+    "types-python-dateutil",
+    "types-lxml",
+    "types-urllib3",
+]
+speed = [
+    "backports-datetime-fromisoformat; python_version < '3.11'",
+    "faust-cchardet >= 2.1.19",
+    "urllib3[brotli]",
+]
+all = [
+    "htmldate[dev]",
+    "htmldate[speed]",
+]
+
+# [tool.pytest.ini_options]
+# testpaths = "tests/*test*.py"
diff --git a/setup.py b/setup.py
@@ -3,40 +3,11 @@
 http://github.com/adbar/htmldate
 """
 
-import re
 import sys
 
-from pathlib import Path
 from setuptools import setup
 
 
-# some problems with installation solved this way
-extras = {
-    "speed": [
-        "backports-datetime-fromisoformat; python_version < '3.11'",
-        "faust-cchardet >= 2.1.19",
-        "urllib3[brotli]",
-    ],
-}
-extras["all"] = extras["speed"]
-
-
-def get_long_description():
-    "Return the README"
-    with open("README.md", "r", encoding="utf-8") as filehandle:
-        long_description = filehandle.read()
-    # long_description += "\n\n"
-    # with open("CHANGELOG.md", encoding="utf8") as f:
-    #    long_description += f.read()
-    return long_description
-
-
-def get_version(package):
-    "Return package version as listed in `__version__` in `init.py`"
-    initfile = Path(package, "__init__.py").read_text()
-    return re.search("__version__ = ['\"]([^'\"]+)['\"]", initfile)[1]
-
-
 # add argument to compile with mypyc
 if len(sys.argv) > 1 and sys.argv[1] == "--use-mypyc":
     sys.argv.pop(1)
@@ -48,6 +19,7 @@ def get_version(package):
             "htmldate/__init__.py",
             "htmldate/core.py",
             "htmldate/extractors.py",
+            "htmldate/meta.py",
             "htmldate/settings.py",
             "htmldate/utils.py",
             "htmldate/validators.py",
@@ -60,74 +32,6 @@ def get_version(package):
 
 
 setup(
-    name="htmldate",
-    version=get_version("htmldate"),
-    description="Fast and robust extraction of original and updated publication dates from URLs and web pages.",
-    long_description=get_long_description(),
-    long_description_content_type="text/markdown",
-    classifiers=[
-        # As from http://pypi.python.org/pypi?%3Aaction=list_classifiers
-        "Development Status :: 5 - Production/Stable",
-        # 'Development Status :: 6 - Mature',
-        "Environment :: Console",
-        "Intended Audience :: Developers",
-        "Intended Audience :: Education",
-        "Intended Audience :: Information Technology",
-        "Intended Audience :: Science/Research",
-        "License :: OSI Approved :: Apache Software License",
-        "Operating System :: MacOS :: MacOS X",
-        "Operating System :: Microsoft :: Windows",
-        "Operating System :: POSIX :: Linux",
-        "Programming Language :: Python",
-        "Programming Language :: Python :: 3",
-        "Programming Language :: Python :: 3.8",
-        "Programming Language :: Python :: 3.9",
-        "Programming Language :: Python :: 3.10",
-        "Programming Language :: Python :: 3.11",
-        "Programming Language :: Python :: 3.12",
-        "Topic :: Internet :: WWW/HTTP",
-        "Topic :: Scientific/Engineering :: Information Analysis",
-        "Topic :: Text Processing :: Linguistic",
-        "Topic :: Text Processing :: Markup :: HTML",
-    ],
-    keywords=[
-        "datetime",
-        "date-parser",
-        "entity-extraction",
-        "html-extraction",
-        "html-parsing",
-        "metadata-extraction",
-        "webarchives",
-        "web-scraping",
-    ],
-    url="https://htmldate.readthedocs.io",
-    project_urls={
-        "Source": "https://github.com/adbar/htmldate",
-        "Tracker": "https://github.com/adbar/htmldate/issues",
-        "Blog": "https://adrien.barbaresi.eu/blog/tag/htmldate.html",
-    },
-    author="Adrien Barbaresi",
-    author_email="barbaresi@bbaw.de",
-    license="Apache-2.0",
-    packages=["htmldate"],
-    include_package_data=True,
-    python_requires=">=3.8",
-    install_requires=[
-        "charset_normalizer >= 3.3.2",
-        "dateparser >= 1.1.2",  # 1.1.3+ slower
-        # see tests on Github Actions
-        "lxml == 4.9.2 ; platform_system == 'Darwin' and python_version <= '3.8'",
-        "lxml >= 5.2.2, < 6 ; platform_system != 'Darwin' or python_version > '3.8'",
-        "python-dateutil >= 2.8.2",
-        "urllib3 >= 1.26, < 3",
-    ],
-    extras_require=extras,
-    entry_points={
-        "console_scripts": ["htmldate=htmldate.cli:main"],
-    },
-    # platforms='any',
-    tests_require=["pytest"],
-    zip_safe=False,
-    # optional use of mypyc
+    # mypyc or not
     ext_modules=ext_modules,
 )