feat: set up Python testing infrastructure with Poetry and pytest

.coveragerc

@@ -0,0 +1,30 @@
+[run]
+source = sbin
+omit = 
+    */tests/*
+    */__pycache__/*
+    */venv/*
+    */.venv/*
+
+[report]
+exclude_lines =
+    pragma: no cover
+    def __repr__
+    if self.debug:
+    if settings.DEBUG
+    raise AssertionError
+    raise NotImplementedError
+    if 0:
+    if __name__ == .__main__.:
+    if TYPE_CHECKING:
+    class .*\bProtocol\):
+    @(abc\\.)?abstractmethod
+show_missing = true
+precision = 2
+# fail_under = 80  # Enable this when you have actual tests
+
+[html]
+directory = htmlcov
+
+[xml]
+output = coverage.xml

.gitignore

@@ -0,0 +1,69 @@
+# Python
+__pycache__/
+*.py[cod]
+*$py.class
+*.so
+.Python
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# Virtual environments
+venv/
+.venv/
+ENV/
+env/
+.env
+
+# Testing
+.pytest_cache/
+.coverage
+htmlcov/
+coverage.xml
+*.cover
+.hypothesis/
+.tox/
+
+# IDEs
+.idea/
+.vscode/
+*.swp
+*.swo
+*~
+.project
+.pydevproject
+.settings/
+
+# OS
+.DS_Store
+Thumbs.db
+
+# Claude
+.claude/*
+
+# Build artifacts
+build/
+*.log
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/

pyproject.toml

@@ -0,0 +1,72 @@
+[tool.poetry]
+name = "ml-interpretability-papers"
+version = "0.1.0"
+description = "Machine Learning Interpretability Papers Collection"
+authors = ["Your Name <[email protected]>"]
+readme = "README.org"
+packages = [{include = "sbin"}]
+
+[tool.poetry.dependencies]
+python = "^3.8"
+
+[tool.poetry.group.dev.dependencies]
+pytest = "^8.0.0"
+pytest-cov = "^5.0.0"
+pytest-mock = "^3.14.0"
+
+[tool.poetry.scripts]
+test = "pytest:main"
+tests = "pytest:main"
+
+[tool.pytest.ini_options]
+minversion = "8.0"
+addopts = [
+    "-ra",
+    "--strict-markers",
+    "--strict-config",
+]
+testpaths = ["tests"]
+python_files = ["test_*.py", "*_test.py"]
+python_classes = ["Test*"]
+python_functions = ["test_*"]
+markers = [
+    "unit: marks tests as unit tests (fast, isolated)",
+    "integration: marks tests as integration tests (may require external resources)",
+    "slow: marks tests as slow running",
+]
+
+[tool.coverage.run]
+source = ["sbin"]
+omit = [
+    "*/tests/*",
+    "*/__pycache__/*",
+    "*/venv/*",
+    "*/.venv/*",
+]
+
+[tool.coverage.report]
+exclude_lines = [
+    "pragma: no cover",
+    "def __repr__",
+    "if self.debug:",
+    "if settings.DEBUG",
+    "raise AssertionError",
+    "raise NotImplementedError",
+    "if 0:",
+    "if __name__ == .__main__.:",
+    "if TYPE_CHECKING:",
+    "class .*\\bProtocol\\):",
+    "@(abc\\.)?abstractmethod",
+]
+show_missing = true
+precision = 2
+
+[tool.coverage.html]
+directory = "htmlcov"
+
+[tool.coverage.xml]
+output = "coverage.xml"
+
+[build-system]
+requires = ["poetry-core"]
+build-backend = "poetry.core.masonry.api"

sbin/__init__.py

@@ -0,0 +1 @@
+"""ML Interpretability Papers package."""

tests/conftest.py

@@ -0,0 +1,100 @@
+"""Shared pytest fixtures and configuration."""
+
+import json
+import os
+import tempfile
+from pathlib import Path
+from typing import Generator, Dict, Any
+
+import pytest
+
+
+@pytest.fixture
+def temp_dir() -> Generator[Path, None, None]:
+    """Create a temporary directory for testing."""
+    with tempfile.TemporaryDirectory() as tmpdir:
+        yield Path(tmpdir)
+
+
+@pytest.fixture
+def sample_cache_data() -> Dict[str, Any]:
+    """Provide sample cache data for testing."""
+    return {
+        "a:1234.5678": {
+            "0KEY_": "a:1234.5678",
+            "GetRecord": {
+                "record": {
+                    "header": {
+                        "identifier": "oai:arXiv.org:1234.5678"
+                    },
+                    "metadata": {
+                        "arXiv": {
+                            "title": "Sample Paper Title",
+                            "authors": {
+                                "author": [
+                                    {"keyname": "Doe", "forenames": "John"},
+                                    {"keyname": "Smith", "forenames": "Jane"}
+                                ]
+                            },
+                            "created": "2023-01-01"
+                        }
+                    }
+                }
+            }
+        }
+    }
+
+
+@pytest.fixture
+def sample_cache_file(temp_dir: Path, sample_cache_data: Dict[str, Any]) -> Path:
+    """Create a sample cache file for testing."""
+    cache_file = temp_dir / "test_cache.jsonl"
+    with open(cache_file, 'w') as f:
+        for key, value in sample_cache_data.items():
+            f.write(json.dumps(value) + '\n')
+    return cache_file
+
+
+@pytest.fixture
+def sample_readme_template(temp_dir: Path) -> Path:
+    """Create a sample README template for testing."""
+    template_file = temp_dir / "test_template.org"
+    content = """* Machine Learning Interpretability Papers
+
+** Papers
++ {"arxiv_id": "1234.5678"}
++ {"doi": "10.1234/sample"}
++ {"sems_id": "sample-semantic-id"}
+
+** Other Content
+This is some other content.
+"""
+    template_file.write_text(content)
+    return template_file
+
+
+@pytest.fixture
+def mock_http_response(mocker):
+    """Mock HTTP responses for external API calls."""
+    def _mock_response(url: str, data: Any, status_code: int = 200):
+        mock_response = mocker.Mock()
+        mock_response.read.return_value = json.dumps(data).encode('utf-8') if isinstance(data, dict) else data
+        mock_response.status = status_code
+        return mock_response
+    return _mock_response
+
+
+@pytest.fixture
+def mock_env_vars(monkeypatch):
+    """Fixture to easily set environment variables for testing."""
+    def _set_env(**kwargs):
+        for key, value in kwargs.items():
+            monkeypatch.setenv(key, str(value))
+    return _set_env
+
+
+@pytest.fixture
+def isolated_filesystem(temp_dir: Path, monkeypatch) -> Path:
+    """Create an isolated filesystem for testing with proper working directory."""
+    monkeypatch.chdir(temp_dir)
+    return temp_dir

tests/test_setup_validation.py

@@ -0,0 +1,67 @@
+"""Validation tests to ensure the testing infrastructure is set up correctly."""
+
+import sys
+from pathlib import Path
+
+import pytest
+
+
+class TestSetupValidation:
+    """Test suite to validate the testing infrastructure setup."""
+
+    def test_pytest_installed(self):
+        """Verify pytest is installed and importable."""
+        import pytest
+        assert pytest.__version__
+
+    def test_pytest_cov_installed(self):
+        """Verify pytest-cov is installed and importable."""
+        import pytest_cov
+        assert pytest_cov
+
+    def test_pytest_mock_installed(self):
+        """Verify pytest-mock is installed and importable."""
+        import pytest_mock
+        assert pytest_mock
+
+    def test_project_structure(self):
+        """Verify the project structure is set up correctly."""
+        workspace = Path(__file__).parent.parent
+
+        # Check main directories exist
+        assert workspace.exists()
+        assert (workspace / "tests").exists()
+        assert (workspace / "tests" / "unit").exists()
+        assert (workspace / "tests" / "integration").exists()
+        assert (workspace / "sbin").exists()
+
+        # Check important files exist
+        assert (workspace / "pyproject.toml").exists()
+        assert (workspace / "tests" / "__init__.py").exists()
+        assert (workspace / "tests" / "conftest.py").exists()
+
+    def test_conftest_fixtures(self, temp_dir, sample_cache_data):
+        """Verify conftest fixtures are working."""
+        assert temp_dir.exists()
+        assert isinstance(sample_cache_data, dict)
+        assert "a:1234.5678" in sample_cache_data
+
+    @pytest.mark.unit
+    def test_unit_marker(self):
+        """Test that the unit marker is registered."""
+        pass
+
+    @pytest.mark.integration
+    def test_integration_marker(self):
+        """Test that the integration marker is registered."""
+        pass
+
+    @pytest.mark.slow
+    def test_slow_marker(self):
+        """Test that the slow marker is registered."""
+        pass
+
+    def test_python_path(self):
+        """Verify the Python path includes the project root."""
+        workspace = Path(__file__).parent.parent
+        assert str(workspace) in sys.path or str(workspace.absolute()) in sys.path