feat: Add comprehensive Python testing infrastructure with Poetry

.gitignore

@@ -45,6 +45,9 @@ nosetests.xml
 coverage.xml
 *.cover
 .hypothesis/
+.pytest_cache/
+*.pytest_cache
+.pytest_cache/*
 
 # Translations
 *.mo
@@ -119,3 +122,13 @@ credentials.json
 
 # Default work dir
 work
+
+# Poetry
+poetry.lock
+
+# Claude settings
+.claude/*
+
+# Testing artifacts
+test-results/
+.benchmarks/

Makefile

@@ -0,0 +1,17 @@
+.PHONY: test tests coverage clean
+
+test:
+	poetry run pytest
+
+tests:
+	poetry run pytest
+
+coverage:
+	poetry run pytest --cov-report=term-missing --cov-report=html
+
+clean:
+	rm -rf .pytest_cache
+	rm -rf htmlcov
+	rm -f coverage.xml
+	rm -f .coverage
+	find . -type d -name "__pycache__" -exec rm -rf {} + 2>/dev/null || true

pyproject.toml

@@ -0,0 +1,168 @@
+[tool.poetry]
+name = "soweego"
+version = "1.0.0"
+description = "A Wikidata bot for entity linking"
+authors = ["Marco Fossati <[email protected]>"]
+license = "GPL-3.0"
+readme = "README.md"
+repository = "https://github.com/Wikidata/soweego"
+keywords = ["wikidata", "entity-linking", "record-linkage"]
+classifiers = [
+    "Development Status :: 5 - Production/Stable",
+    "License :: OSI Approved :: GNU General Public License v3 (GPLv3)",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.8",
+    "Programming Language :: Python :: 3.9",
+    "Programming Language :: Python :: 3.10",
+    "Topic :: Scientific/Engineering :: Information Analysis",
+]
+packages = [{include = "soweego"}]
+
+[tool.poetry.dependencies]
+python = "^3.8.1"
+click = "^8.0.0"
+jellyfish = "^0.9.0"
+joblib = "^1.0.0"
+keras = "^2.0.0"
+lxml = "^4.0.0"
+mlens = "^0.2.0"
+numpy = "^1.0.0"
+pandas = "^1.0.0"
+pywikibot = "^7.0.0"
+recordlinkage = "^0.15.0"
+regex = "^2022.0.0"
+requests = "^2.0.0"
+scikit-learn = "^1.0.0"
+sqlalchemy = "^1.4.0"
+tensorflow = "^2.0.0"
+tqdm = "^4.0.0"
+urllib3 = "^1.26.0"
+matplotlib = "^3.0.0"
+seaborn = "^0.11.0"
+
+[tool.poetry.group.dev.dependencies]
+pytest = "^7.4.0"
+pytest-cov = "^4.1.0"
+pytest-mock = "^3.11.0"
+black = "^23.0.0"
+isort = "^5.12.0"
+flake8 = "^6.0.0"
+mypy = "^1.4.0"
+pre-commit = "^3.3.0"
+
+[tool.poetry.scripts]
+soweego = "soweego.cli:cli"
+
+[build-system]
+requires = ["poetry-core>=1.0.0"]
+build-backend = "poetry.core.masonry.api"
+
+[tool.pytest.ini_options]
+minversion = "7.0"
+testpaths = ["tests"]
+python_files = ["test_*.py", "*_test.py"]
+python_classes = ["Test*"]
+python_functions = ["test_*"]
+addopts = [
+    "-ra",
+    "--strict-markers",
+    "--strict-config",
+    "--cov=soweego",
+    "--cov-branch",
+    "--cov-report=term-missing:skip-covered",
+    "--cov-report=html:htmlcov",
+    "--cov-report=xml:coverage.xml",
+    # "--cov-fail-under=80",  # Uncomment when actual tests are written
+    "-vv"
+]
+markers = [
+    "unit: Unit tests",
+    "integration: Integration tests",
+    "slow: Slow running tests"
+]
+filterwarnings = [
+    "ignore::DeprecationWarning",
+    "ignore::PendingDeprecationWarning"
+]
+
+[tool.coverage.run]
+source = ["soweego"]
+branch = true
+parallel = true
+omit = [
+    "*/tests/*",
+    "*/test_*.py",
+    "*/__pycache__/*",
+    "*/site-packages/*",
+    "*/distutils/*",
+    "*/.venv/*",
+    "*/venv/*"
+]
+
+[tool.coverage.report]
+precision = 2
+show_missing = true
+skip_covered = true
+# fail_under = 80  # Uncomment when actual tests are written
+exclude_lines = [
+    "pragma: no cover",
+    "def __repr__",
+    "def __str__",
+    "raise AssertionError",
+    "raise NotImplementedError",
+    "if __name__ == .__main__.:",
+    "if TYPE_CHECKING:",
+    "if typing.TYPE_CHECKING:",
+    "@abstractmethod",
+    "@abc.abstractmethod",
+    "except ImportError:",
+    "pass"
+]
+
+[tool.coverage.html]
+directory = "htmlcov"
+
+[tool.coverage.xml]
+output = "coverage.xml"
+
+[tool.isort]
+profile = "black"
+line_length = 88
+multi_line_output = 3
+include_trailing_comma = true
+force_grid_wrap = 0
+use_parentheses = true
+ensure_newline_before_comments = true
+
+[tool.black]
+line-length = 88
+target-version = ['py38', 'py39', 'py310']
+include = '\.pyi?$'
+exclude = '''
+/(
+    \.eggs
+  | \.git
+  | \.hg
+  | \.mypy_cache
+  | \.tox
+  | \.venv
+  | _build
+  | buck-out
+  | build
+  | dist
+  | tests/fixtures
+)/
+'''
+
+[tool.mypy]
+python_version = "3.8"
+warn_return_any = true
+warn_unused_configs = true
+disallow_untyped_defs = false
+disallow_any_generics = false
+ignore_missing_imports = true
+no_implicit_optional = true
+warn_redundant_casts = true
+warn_unused_ignores = true
+warn_unreachable = true
+strict_equality = true