feat: Set up comprehensive Python testing infrastructure with Poetry

.gitignore

@@ -14,3 +14,48 @@ AUTHORS
 ChangeLog
 .DS_Store
 .mypy_cache
+
+# Testing artifacts
+.pytest_cache/
+.coverage
+htmlcov/
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+pytest_cache/
+
+# Claude settings
+.claude/*
+
+# Poetry
+# Note: Do not ignore poetry.lock - it should be committed
+
+# Virtual environments
+venv/
+ENV/
+env/
+.venv/
+.env
+
+# IDE specific files
+.vscode/
+*.sublime-project
+*.sublime-workspace
+
+# Build artifacts
+__pycache__/
+*.so
+*.dylib
+*.dll
+
+# OS specific
+Thumbs.db
+.DS_Store
+Desktop.ini
+
+# Temporary files
+*.tmp
+*.temp
+*.log
+.cache/

pyproject.toml

@@ -0,0 +1,124 @@
+[tool.poetry]
+name = "tensorflow-transform"
+version = "1.17.1"
+description = "A library for data preprocessing with TensorFlow"
+authors = ["Google Inc. <tensorflow-extended-dev@googlegroups.com>"]
+license = "Apache-2.0"
+readme = "README.md"
+homepage = "https://www.tensorflow.org/tfx/transform/get_started"
+repository = "https://github.com/tensorflow/transform"
+keywords = ["tensorflow", "transform", "tfx"]
+classifiers = [
+    "Development Status :: 5 - Production/Stable",
+    "Intended Audience :: Developers",
+    "Intended Audience :: Education",
+    "Intended Audience :: Science/Research",
+    "License :: OSI Approved :: Apache Software License",
+    "Operating System :: OS Independent",
+    "Programming Language :: Python",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.9",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3 :: Only",
+    "Topic :: Scientific/Engineering",
+    "Topic :: Scientific/Engineering :: Artificial Intelligence",
+    "Topic :: Scientific/Engineering :: Mathematics",
+    "Topic :: Software Development",
+    "Topic :: Software Development :: Libraries",
+    "Topic :: Software Development :: Libraries :: Python Modules",
+]
+packages = [{include = "tensorflow_transform"}]
+
+[tool.poetry.dependencies]
+python = ">=3.9,<4"
+absl-py = ">=0.9,<2.0.0"
+apache-beam = {version = ">=2.53,<3", extras = ["gcp"], python = ">=3.11"}
+numpy = ">=1.22.0"
+protobuf = [
+    {version = ">=4.25.2,<6.0.0", python = ">=3.11"},
+    {version = ">=4.21.6,<6.0.0", python = "<3.11"}
+]
+pyarrow = ">=10,<11"
+pydot = ">=1.2,<2"
+tensorflow = ">=2.17,<2.18"
+tensorflow-metadata = ">=1.15.0"
+tf-keras = ">=2"
+tfx-bsl = ">=1.15.0"
+
+[tool.poetry.group.dev.dependencies]
+pytest = "^8.0.0"
+pytest-cov = "^4.1.0"
+pytest-mock = "^3.12.0"
+
+[tool.poetry.scripts]
+test = "pytest:main"
+tests = "pytest:main"
+
+[tool.pytest.ini_options]
+minversion = "8.0"
+addopts = [
+    "--strict-markers",
+    "--tb=short",
+    "--cov=tensorflow_transform",
+    "--cov-report=term-missing:skip-covered",
+    "--cov-report=html",
+    "--cov-report=xml",
+    "--cov-fail-under=80",
+    "--doctest-modules",
+    "-v"
+]
+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 (deselect with '-m \"not slow\"')"
+]
+filterwarnings = [
+    "ignore::DeprecationWarning",
+    "ignore::PendingDeprecationWarning"
+]
+
+[tool.coverage.run]
+source = ["tensorflow_transform"]
+branch = true
+parallel = true
+omit = [
+    "*/tests/*",
+    "*/test_*.py",
+    "*/*_test.py",
+    "*/setup.py",
+    "*/version.py",
+    "*/__pycache__/*",
+    "*/site-packages/*"
+]
+
+[tool.coverage.report]
+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"
+]
+precision = 2
+skip_covered = true
+show_missing = true
+
+[tool.coverage.html]
+directory = "htmlcov"
+
+[tool.coverage.xml]
+output = "coverage.xml"
+
+[build-system]
+requires = ["poetry-core>=1.0.0"]
+build-backend = "poetry.core.masonry.api"

tests/README.md

@@ -0,0 +1,94 @@
+# TensorFlow Transform Testing Infrastructure
+
+This directory contains the testing infrastructure for TensorFlow Transform.
+
+## Structure
+
+```
+tests/
+├── README.md               # This file
+├── __init__.py            # Package marker
+├── conftest.py            # Shared pytest fixtures and configuration
+├── test_setup_validation.py  # Full validation tests (requires all dependencies)
+├── test_minimal_setup.py     # Minimal tests that work without all dependencies
+├── unit/                  # Unit tests directory
+│   └── __init__.py
+└── integration/           # Integration tests directory
+    └── __init__.py
+```
+
+## Running Tests
+
+### Using Poetry Scripts
+
+```bash
+# Run all tests
+poetry run test
+
+# Alternative command (both work)
+poetry run tests
+
+# Run specific test file
+poetry run test tests/test_minimal_setup.py
+
+# Run with specific markers
+poetry run test -m unit
+poetry run test -m "not slow"
+```
+
+### Using pytest directly
+
+```bash
+# Run all tests
+python -m pytest
+
+# Run with coverage
+python -m pytest --cov=tensorflow_transform
+
+# Run without coverage (useful for debugging)
+python -m pytest --no-cov
+```
+
+## Test Markers
+
+- `@pytest.mark.unit` - Fast, isolated unit tests
+- `@pytest.mark.integration` - Integration tests that may require external resources
+- `@pytest.mark.slow` - Tests that take a long time to run
+
+## Available Fixtures
+
+See `conftest.py` for all available fixtures. Key fixtures include:
+
+- `temp_dir` - Temporary directory that's cleaned up after test
+- `temp_file` - Temporary file that's cleaned up after test
+- `mock_config` - Sample configuration dictionary
+- `sample_data` - Sample data for testing transformations
+- `tf_example_data` - Temporary TFRecord file with example data
+- `mock_preprocessing_fn` - Simple preprocessing function for testing
+- `mock_schema` - Simple schema for testing
+
+## Coverage Configuration
+
+Coverage is configured to:
+- Require 80% minimum coverage
+- Generate HTML reports in `htmlcov/`
+- Generate XML report as `coverage.xml`
+- Exclude test files and common patterns from coverage
+
+## Known Issues
+
+### ARM64 Architecture Support
+
+Some dependencies like `tfx-bsl` may not have pre-built wheels for ARM64 architecture (e.g., Apple Silicon Macs, ARM Linux). If you encounter installation issues:
+
+1. Try running the minimal test suite: `poetry run test tests/test_minimal_setup.py --no-cov`
+2. Consider using x86_64 emulation or a compatible environment
+3. Build dependencies from source if needed
+
+## Writing New Tests
+
+1. Place unit tests in `tests/unit/`
+2. Place integration tests in `tests/integration/`
+3. Use appropriate markers (`@pytest.mark.unit`, etc.)
+4. Import and use fixtures from `conftest.py`
+5. Follow existing test patterns and naming conventions