maintenance: update setup and use pyproject.toml (#138)

* maintenance: replace setup.py by pyproject.toml

* update dev dependencies

* update descriptors and remove requirements-dev.txt

* fix syntax

.github/workflows/tests.yml

@@ -55,8 +55,8 @@ jobs:
     # package setup
     - uses: actions/checkout@v4
 
-    - name: Install dependencies
-      run: pip install -r requirements-dev.txt
+    - name: Install package and dependencies
+      run: pip install .[dev]
 
     # tests
     - name: Lint with flake8
@@ -77,7 +77,7 @@ jobs:
 
     # coverage with default version
     - name: Upload coverage to Codecov
-      if: matrix.python-version == '3.10'
+      if: matrix.python-version == '3.11'
       uses: codecov/codecov-action@v4
       env:
         CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}

MANIFEST.in

@@ -1,7 +1,4 @@
-include CITATION.cff
-include HISTORY.rst
-include LICENSE
-include README.md
+include CITATION.cff HISTORY.rst LICENSE README.md
 include licenses/
 include simplemma/py.typed
 graft simplemma/strategies/

pyproject.toml

@@ -0,0 +1,123 @@
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "simplemma"
+description = "A lightweight toolkit for multilingual lemmatization and language detection."
+readme = "README.md"
+license = { text = "MIT License" }
+dynamic = ["version"]
+requires-python = ">=3.8"
+authors = [
+  {name = "Adrien Barbaresi", email = "[email protected]"}
+]
+keywords=[
+    "language detection",
+    "language identification",
+    "langid",
+    "lemmatization",
+    "lemmatizer",
+    "lemmatiser",
+    "nlp",
+    "tokenization",
+    "tokenizer",
+]
+classifiers = [
+    # https://pypi.org/classifiers/
+    "Development Status :: 4 - Beta",
+    "Intended Audience :: Developers",
+    "Intended Audience :: Education",
+    "Intended Audience :: Information Technology",
+    "Intended Audience :: Science/Research",
+    "License :: OSI Approved :: MIT License",
+    "Natural Language :: Bulgarian",
+    "Natural Language :: Catalan",
+    "Natural Language :: Croatian",
+    "Natural Language :: Czech",
+    "Natural Language :: Danish",
+    "Natural Language :: Dutch",
+    "Natural Language :: English",
+    "Natural Language :: Finnish",
+    "Natural Language :: French",
+    "Natural Language :: Galician",
+    "Natural Language :: German",
+    "Natural Language :: Greek",
+    "Natural Language :: Hindi",
+    "Natural Language :: Hungarian",
+    "Natural Language :: Icelandic",
+    "Natural Language :: Indonesian",
+    "Natural Language :: Irish",
+    "Natural Language :: Italian",
+    "Natural Language :: Latin",
+    "Natural Language :: Latvian",
+    "Natural Language :: Lithuanian",
+    "Natural Language :: Macedonian",
+    "Natural Language :: Malay",
+    "Natural Language :: Norwegian",
+    "Natural Language :: Polish",
+    "Natural Language :: Portuguese",
+    "Natural Language :: Romanian",
+    "Natural Language :: Russian",
+    "Natural Language :: Slovak",
+    "Natural Language :: Slovenian",
+    "Natural Language :: Spanish",
+    "Natural Language :: Swedish",
+    "Natural Language :: Thai",
+    "Natural Language :: Turkish",
+    "Natural Language :: Ukrainian",
+    "Operating System :: OS Independent",
+    "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",
+    "Programming Language :: Python :: 3.13",
+    "Topic :: Scientific/Engineering :: Information Analysis",
+    "Topic :: Software Development :: Internationalization",
+    "Topic :: Software Development :: Localization",
+    "Topic :: Text Processing :: Linguistic",
+    "Typing :: Typed",
+]
+dependencies = []
+
+# https://setuptools.pypa.io/en/latest/userguide/pyproject_config.html
+[tool.setuptools]
+packages = ["simplemma"]
+
+[tool.setuptools.package-data]
+simplemma = ["strategies/dictionaries/data/*.plzma"]
+
+# https://packaging.python.org/en/latest/guides/single-sourcing-package-version/
+[tool.setuptools.dynamic]
+version = {attr = "simplemma.__version__"}
+
+[project.urls]
+"Homepage" = "https://github.com/adbar/simplemma"
+"Docs" = "https://adbar.github.io/simplemma/"
+"Blog" = "https://adrien.barbaresi.eu/blog/"
+
+[project.optional-dependencies]
+marisa-trie = [
+    "marisa_trie == 1.2.0",
+    "platformdirs == 4.2.2",
+]
+test = [
+    "simplemma[marisa-trie]",
+    "pytest == 8.3.2",
+    "pytest-cov == 5.0.0",
+]
+dev = [
+    "simplemma[test]",
+    "black == 24.8.0",
+    "flake8 == 7.1.1",
+    "mypy == 1.11.0",
+    "types-requests == 2.32.0.20240712",
+]
+docs = [
+    "mkdocs",
+    "mkdocs-material",
+    "mkdocstrings",
+    "mkdocstrings-python",
+]