Transition from using setup.py to pyproject.toml to specify project metadata

.github/workflows/readme.yml

@@ -22,5 +22,6 @@ jobs:
       run: |
           python -m pip install --upgrade pip
           python -m pip install invoke rundoc .
+          python -m pip install toml
     - name: Run the README.md
       run: invoke readme

Dockerfile

@@ -8,7 +8,7 @@ RUN mkdir /SDGym && \
     mkdir /SDGym/sdgym && \
 
 # Copy code
-COPY setup.py README.md HISTORY.md MANIFEST.in LICENSE Makefile setup.cfg /SDGym/
+COPY pyproject.toml README.md HISTORY.md MANIFEST.in LICENSE Makefile setup.cfg /SDGym/
 COPY /sdgym/ /SDGym/sdgym
 
 WORKDIR /SDGym

Makefile

@@ -123,8 +123,7 @@ coverage: ## check code coverage quickly with the default Python
 
 .PHONY: dist
 dist: clean ## builds source and wheel package
-	python setup.py sdist
-	python setup.py bdist_wheel
+	python -m build --wheel --sdist
 	ls -l dist
 
 .PHONY: publish-confirm

setup.py → pyproject.toml

@@ -1,17 +1,29 @@
-#!/usr/bin/env python
-# -*- coding: utf-8 -*-
-
-"""The setup script."""
-
-from setuptools import find_packages, setup
-
-with open('README.md', encoding='utf-8') as readme_file:
-    readme = readme_file.read()
-
-with open('HISTORY.md', encoding='utf-8') as history_file:
-    history = history_file.read()
-
-install_requires = [
+[build-system]
+requires = ['setuptools', 'wheel']
+build-backend = 'setuptools.build_meta'
+
+[project]
+name = 'sdgym'
+description = 'Benchmark tabular synthetic data generators using a variety of datasets'
+authors = [{ name = 'DataCebo, Inc.', email = '[email protected]' }]
+classifiers = [
+    'Development Status :: 2 - Pre-Alpha',
+    'Intended Audience :: Developers',
+    'License :: Free for non-commercial use',
+    'Natural Language :: English',
+    'Programming Language :: Python :: 3',
+    'Programming Language :: Python :: 3.8',
+    'Programming Language :: Python :: 3.9',
+    'Programming Language :: Python :: 3.10',
+    'Programming Language :: Python :: 3.11',
+    'Topic :: Scientific/Engineering :: Artificial Intelligence',
+]
+keywords = ['machine learning', 'synthetic data generation', 'benchmark', 'generative models']
+version = '0.7.1.dev0'
+license = { text = 'BSL-1.1' }
+requires-python = '>=3.8,<3.12'
+readme = 'README.md'
+dependencies = [
     'appdirs>=1.3,<2',
     'boto3>=1.15.0,<2',
     'botocore>=1.18,<2',
@@ -38,24 +50,29 @@
     'sdv>=1.3.0,<2',
 ]
 
+[project.urls]
+"Source Code"= "https://github.com/sdv-dev/SDGym/"
+"Issue Tracker" = "https://github.com/sdv-dev/SDGym/issues"
+"Twitter" = "https://twitter.com/sdv_dev"
+"Chat" = "https://bit.ly/sdv-slack-invite"
 
-dask_requires = [
-    'dask',
-    'distributed',
-]
+[project.entry-points]
+sdgym = { main = 'sdgym.cli.__main__:main' }
 
-setup_requires = [
-    'pytest-runner>=2.11.1',
-]
+[project.optional-dependencies]
+dask = ['dask', 'distributed']
 
-tests_require = [
+test = [
     'pytest>=3.4.2',
     'pytest-cov>=2.6.0',
     'jupyter>=1.0.0,<2',
     'rundoc>=0.4.3,<0.5',
+    'toml>=0.10.2,<1',
 ]
 
-development_requires = [
+dev = [
+    'sdgym[dask, test]',
+
     # general
     'bumpversion>=0.5.3,<0.6',
     'pip>=9.0.1',
@@ -102,48 +119,24 @@
     'invoke',
 ]
 
-setup(
-    author='DataCebo, Inc.',
-    author_email='[email protected]',
-    classifiers=[
-        'Development Status :: 2 - Pre-Alpha',
-        'Intended Audience :: Developers',
-        'License :: Free for non-commercial use',
-        'Natural Language :: English',
-        'Programming Language :: Python :: 3',
-        'Programming Language :: Python :: 3.8',
-        'Programming Language :: Python :: 3.9',
-        'Programming Language :: Python :: 3.10',
-        'Programming Language :: Python :: 3.11',
-        'Topic :: Scientific/Engineering :: Artificial Intelligence',
-    ],
-    description=(
-        'Benchmark tabular synthetic data generators using a variety of datasets'
-    ),
-    entry_points={
-        'console_scripts': [
-            'sdgym=sdgym.cli.__main__:main'
-        ],
-    },
-    extras_require={
-        'all': development_requires + tests_require + dask_requires,
-        'dev': development_requires + tests_require + dask_requires,
-        'test': tests_require,
-        'dask': dask_requires,
-    },
-    include_package_data=True,
-    install_requires=install_requires,
-    license='BSL-1.1',
-    long_description=readme + '\n\n' + history,
-    long_description_content_type='text/markdown',
-    keywords='machine learning synthetic data generation benchmark generative models',
-    name='sdgym',
-    packages=find_packages(include=['sdgym', 'sdgym.*']),
-    python_requires='>=3.8,<3.12',
-    setup_requires=setup_requires,
-    test_suite='tests',
-    tests_require=tests_require,
-    url='https://github.com/sdv-dev/SDGym',
-    version='0.7.1.dev0',
-    zip_safe=False,
-)
+all = [
+    'sdgym[dask, test, dev]',
+]
+
+[tool.setuptools]
+include-package-data = true
+
+[tool.setuptools.packages.find]
+include = ['sdgym', 'sdgym.*']
+namespaces = false
+
+[tool.isort]
+line_length = 99
+lines_between_types = 0
+multi_line_output = 4
+not_skip = ['__init__.py']
+use_parentheses = true
+
+[tool.pydocstyle]
+convention = 'google'
+add-ignore = ['D107', 'D407', 'D417']

setup.cfg

@@ -16,7 +16,7 @@ values =
 
 [bumpversion:part:candidate]
 
-[bumpversion:file:setup.py]
+[bumpversion:file:pyproject.toml]
 search = version='{current_version}'
 replace = version='{new_version}'
 
@@ -36,17 +36,5 @@ extend-ignore = D105,  # Missing docstring in magic method
 	PD005,  # Use arithmetic operator instead of method
 	SFS3  # String literal formatting using f-string
 
-[isort]
-line_length = 99
-lines_between_types = 0
-multi_line_output = 4
-not_skip = __init__.py
-use_parentheses = True
-
 [aliases]
 test = pytest
-
-[pydocstyle]
-convention = google
-add-ignore = D107, D407, D417
-

tasks.py

@@ -2,14 +2,18 @@
 import inspect
 import operator
 import os
-import re
-import pkg_resources
 import platform
+import re
 import shutil
 import stat
+import sys
 from pathlib import Path
 
+import pkg_resources
+import toml
 from invoke import task
+from packaging.requirements import Requirement
+from packaging.version import Version
 
 COMPARISONS = {
     '>=': operator.ge,
@@ -52,50 +56,44 @@ def readme(c):
     os.chdir(cwd)
     shutil.rmtree(test_path)
 
-
-def _validate_python_version(line):
-    is_valid = True
-    for python_version_match in re.finditer(r"python_version(<=?|>=?|==)\'(\d\.?)+\'", line):
-        python_version = python_version_match.group(0)
-        comparison = re.search(r'(>=?|<=?|==)', python_version).group(0)
-        version_number = python_version.split(comparison)[-1].replace("'", "")
-        comparison_function = COMPARISONS[comparison]
-        is_valid = is_valid and comparison_function(
-            pkg_resources.parse_version(platform.python_version()),
-            pkg_resources.parse_version(version_number),
-        )
-
-    return is_valid
-
+def _get_minimum_versions(dependencies, python_version):
+    min_versions = {}
+    for dependency in dependencies:
+        if '@' in dependency:
+            name, url = dependency.split(' @')
+            min_versions[name] = f'{name} @ {url}'
+            continue
+
+        req = Requirement(dependency)
+        if ';' in dependency:
+            marker = req.marker
+            if marker and not marker.evaluate({'python_version': python_version}):
+                continue  # Skip this dependency if the marker does not apply to the current Python version
+
+        if req.name not in min_versions:
+            min_version = next((spec.version for spec in req.specifier if spec.operator in ('>=', '==')), None)
+            if min_version:
+                min_versions[req.name] = f'{req.name}=={min_version}'
+
+        elif '@' not in min_versions[req.name]:
+            existing_version = Version(min_versions[req.name].split('==')[1])
+            new_version = next((spec.version for spec in req.specifier if spec.operator in ('>=', '==')), existing_version)
+            if new_version > existing_version:
+                min_versions[req.name] = f'{req.name}=={new_version}'  # Change when a valid newer version is found
+
+    return list(min_versions.values())
 
 @task
 def install_minimum(c):
-    with open('setup.py', 'r') as setup_py:
-        lines = setup_py.read().splitlines()
-
-    versions = []
-    started = False
-    for line in lines:
-        if started:
-            if line == ']':
-                started = False
-                continue
-
-            line = line.strip()
-            if _validate_python_version(line):
-                requirement = re.match(r'[^>]*', line).group(0)
-                requirement = re.sub(r"""['",]""", '', requirement)
-                version = re.search(r'>=?(\d\.?)+\w*', line).group(0)
-                if version:
-                    version = re.sub(r'>=?', '==', version)
-                    version = re.sub(r"""['",]""", '', version)
-                    requirement += version
-                versions.append(requirement)
-
-        elif (line.startswith('install_requires = [')):
-            started = True
-
-    c.run(f'python -m pip install {" ".join(versions)}')
+    with open('pyproject.toml', 'r', encoding='utf-8') as pyproject_file:
+        pyproject_data = toml.load(pyproject_file)
+
+    dependencies = pyproject_data.get('project', {}).get('dependencies', [])
+    python_version = '.'.join(map(str, sys.version_info[:2]))
+    minimum_versions = _get_minimum_versions(dependencies, python_version)
+
+    if minimum_versions:
+        c.run(f'python -m pip install {" ".join(minimum_versions)}')
 
 
 @task

tests/test_tasks.py

@@ -0,0 +1,37 @@
+from tasks import _get_minimum_versions
+
+
+def test_get_minimum_versions():
+    """Test the ``_get_minimum_versions`` method.
+
+    The method should return the minimum versions of the dependencies for the given python version.
+    If a library is linked to an URL, the minimum version should be the URL.
+    """
+    # Setup
+    dependencies = [
+        "numpy>=1.20.0,<2;python_version<'3.10'",
+        "numpy>=1.23.3,<2;python_version>='3.10'",
+        "pandas>=1.2.0,<2;python_version<'3.10'",
+        "pandas>=1.3.0,<2;python_version>='3.10'",
+        'humanfriendly>=8.2,<11',
+        'pandas @ git+https://github.com/pandas-dev/pandas.git@master#egg=pandas'
+    ]
+
+    # Run
+    minimum_versions_39 = _get_minimum_versions(dependencies, '3.9')
+    minimum_versions_310 = _get_minimum_versions(dependencies, '3.10')
+
+    # Assert
+    expected_versions_39 = [
+        'numpy==1.20.0',
+        'pandas @ git+https://github.com/pandas-dev/pandas.git@master#egg=pandas',
+        'humanfriendly==8.2',
+    ]
+    expected_versions_310 = [
+        'numpy==1.23.3',
+        'pandas @ git+https://github.com/pandas-dev/pandas.git@master#egg=pandas',
+        'humanfriendly==8.2',
+    ]
+
+    assert minimum_versions_39 == expected_versions_39
+    assert minimum_versions_310 == expected_versions_310