Merge pull request #88 from UnitSeeker/add-testing-infrastructure

feat: Set up comprehensive Python testing infrastructure with Poetry

Author: peng3307165

.gitignore

@@ -145,4 +145,48 @@ dmypy.json
 **/model/text2vec-base-chinese
 
 /data/milvus/db
-/data/mysql/db
+/data/mysql/db
+
+# Testing
+.pytest_cache/
+.coverage
+.coverage.*
+htmlcov/
+coverage.xml
+*.py,cover
+.hypothesis/
+pytest_cache/
+test-results/
+.tox/
+.nox/
+
+# Claude
+.claude/*
+
+# Poetry
+dist/
+
+# Virtual environments
+.venv/
+venv/
+ENV/
+env/
+.env
+
+# IDE
+.vscode/
+.idea/
+*.swp
+*.swo
+*~
+
+# OS
+.DS_Store
+Thumbs.db
+
+# Temporary files
+*.tmp
+*.bak
+*.orig
+tmp/
+temp/

poetry.lock

@@ -0,0 +1,101 @@
+[tool.poetry]
+name = "modelcache"
+version = "0.1.0"
+description = "A caching framework for machine learning models"
+authors = ["ModelCache Team"]
+readme = "README.md"
+packages = [
+    { include = "modelcache" },
+    { include = "modelcache_mm" }
+]
+
+[tool.poetry.dependencies]
+python = "^3.8"
+cachetools = "5.3.1"
+DBUtils = "1.4"
+Flask = "3.0.0"
+numpy = "1.24.4"
+onnxruntime = "1.16.1"
+openai = "0.28.1"
+pymilvus = "2.3.1"
+PyMySQL = "1.1.0"
+Requests = "2.31.0"
+torch = "2.1.1"
+transformers = "4.38.2"
+faiss-cpu = "1.7.4"
+redis = "5.0.1"
+modelscope = "1.14.0"
+fastapi = "0.115.5"
+uvicorn = "0.32.0"
+chromadb = "0.5.23"
+elasticsearch = "7.10.0"
+snowflake-id = "1.0.2"
+
+[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"
+testpaths = ["tests"]
+python_files = ["test_*.py", "*_test.py"]
+python_classes = ["Test*"]
+python_functions = ["test_*"]
+addopts = [
+    "-ra",
+    "--strict-markers",
+    "--cov=modelcache",
+    "--cov=modelcache_mm",
+    "--cov-branch",
+    "--cov-report=term-missing:skip-covered",
+    "--cov-report=html",
+    "--cov-report=xml",
+    "--cov-fail-under=80",
+    "-v"
+]
+markers = [
+    "unit: Unit tests",
+    "integration: Integration tests",
+    "slow: Slow running tests"
+]
+
+[tool.coverage.run]
+source = ["modelcache", "modelcache_mm"]
+omit = [
+    "*/tests/*",
+    "*/test_*",
+    "*/__pycache__/*",
+    "*/site-packages/*",
+    "*/distutils/*",
+    "*/venv/*",
+    "*/.venv/*"
+]
+
+[tool.coverage.report]
+precision = 2
+show_missing = true
+skip_covered = false
+exclude_lines = [
+    "pragma: no cover",
+    "def __repr__",
+    "if __name__ == .__main__.:",
+    "raise AssertionError",
+    "raise NotImplementedError",
+    "if TYPE_CHECKING:",
+    "if typing.TYPE_CHECKING:"
+]
+
+[tool.coverage.html]
+directory = "htmlcov"
+
+[tool.coverage.xml]
+output = "coverage.xml"
+
+[build-system]
+requires = ["poetry-core"]
+build-backend = "poetry.core.masonry.api"

pyproject.toml

@@ -0,0 +1,218 @@
+"""
+Shared pytest fixtures and configuration for modelcache tests.
+"""
+import os
+import tempfile
+import shutil
+from pathlib import Path
+from typing import Iterator, Dict, Any
+import pytest
+from unittest.mock import MagicMock
+
+
+@pytest.fixture
+def temp_dir() -> Iterator[Path]:
+    """
+    Create a temporary directory for test files.
+    
+    Yields:
+        Path: Path to the temporary directory
+    """
+    temp_path = Path(tempfile.mkdtemp())
+    yield temp_path
+    # Cleanup after test
+    if temp_path.exists():
+        shutil.rmtree(temp_path)
+
+
+@pytest.fixture
+def mock_config() -> Dict[str, Any]:
+    """
+    Provide a mock configuration dictionary for testing.
+    
+    Returns:
+        Dict[str, Any]: Mock configuration
+    """
+    return {
+        "cache_dir": "/tmp/test_cache",
+        "max_cache_size": 1000,
+        "ttl": 3600,
+        "embedding_model": "test-model",
+        "similarity_threshold": 0.8,
+        "vector_dimension": 768,
+        "batch_size": 32,
+        "database": {
+            "type": "memory",
+            "host": "localhost",
+            "port": 6379,
+            "password": None
+        }
+    }
+
+
+@pytest.fixture
+def mock_embedding():
+    """
+    Mock embedding object for testing.
+    
+    Returns:
+        MagicMock: Mock embedding with common methods
+    """
+    mock = MagicMock()
+    mock.embed.return_value = [0.1] * 768  # Default 768-dim embedding
+    mock.embed_batch.return_value = [[0.1] * 768] * 10
+    mock.dimension = 768
+    mock.model_name = "test-embedding-model"
+    return mock
+
+
+@pytest.fixture
+def mock_cache_manager():
+    """
+    Mock cache manager for testing.
+    
+    Returns:
+        MagicMock: Mock cache manager with common methods
+    """
+    mock = MagicMock()
+    mock.get.return_value = None
+    mock.set.return_value = True
+    mock.delete.return_value = True
+    mock.clear.return_value = True
+    mock.size.return_value = 0
+    return mock
+
+
+@pytest.fixture
+def sample_vector_data():
+    """
+    Sample vector data for testing vector operations.
+    
+    Returns:
+        Dict[str, Any]: Sample vector data
+    """
+    return {
+        "id": "test_vector_001",
+        "vector": [0.1, 0.2, 0.3, 0.4, 0.5] * 153 + [0.6, 0.7, 0.8],  # 768 dimensions
+        "metadata": {
+            "source": "test",
+            "timestamp": 1234567890,
+            "model": "test-model"
+        }
+    }
+
+
+@pytest.fixture
+def mock_redis_client():
+    """
+    Mock Redis client for testing Redis-based operations.
+    
+    Returns:
+        MagicMock: Mock Redis client
+    """
+    mock = MagicMock()
+    mock.get.return_value = None
+    mock.set.return_value = True
+    mock.delete.return_value = 1
+    mock.exists.return_value = 0
+    mock.expire.return_value = True
+    mock.ttl.return_value = -2
+    return mock
+
+
+@pytest.fixture
+def mock_milvus_client():
+    """
+    Mock Milvus client for testing vector database operations.
+    
+    Returns:
+        MagicMock: Mock Milvus client
+    """
+    mock = MagicMock()
+    mock.create_collection.return_value = True
+    mock.insert.return_value = MagicMock(primary_keys=[1, 2, 3])
+    mock.search.return_value = [[]]
+    mock.query.return_value = []
+    mock.delete.return_value = MagicMock(delete_count=1)
+    return mock
+
+
+@pytest.fixture(autouse=True)
+def reset_environment():
+    """
+    Reset environment variables before each test.
+    """
+    # Store original env vars
+    original_env = os.environ.copy()
+    
+    # Set test environment variables
+    os.environ["MODELCACHE_ENV"] = "test"
+    os.environ["MODELCACHE_LOG_LEVEL"] = "DEBUG"
+    
+    yield
+    
+    # Restore original env vars
+    os.environ.clear()
+    os.environ.update(original_env)
+
+
+@pytest.fixture
+def sample_text_data():
+    """
+    Sample text data for testing text processing.
+    
+    Returns:
+        List[str]: List of sample texts
+    """
+    return [
+        "This is a test sentence for modelcache.",
+        "Machine learning models need efficient caching.",
+        "Vector embeddings help with semantic search.",
+        "Testing is important for code quality.",
+        "PyTest makes testing in Python easier."
+    ]
+
+
+@pytest.fixture
+def mock_http_response():
+    """
+    Mock HTTP response for testing API calls.
+    
+    Returns:
+        MagicMock: Mock response object
+    """
+    mock = MagicMock()
+    mock.status_code = 200
+    mock.json.return_value = {"status": "success", "data": {}}
+    mock.text = '{"status": "success", "data": {}}'
+    mock.headers = {"Content-Type": "application/json"}
+    return mock
+
+
+# Pytest configuration hooks
+def pytest_configure(config):
+    """
+    Configure pytest with custom settings.
+    """
+    # Add custom markers description
+    config.addinivalue_line(
+        "markers", "unit: mark test as a unit test"
+    )
+    config.addinivalue_line(
+        "markers", "integration: mark test as an integration test"
+    )
+    config.addinivalue_line(
+        "markers", "slow: mark test as slow running"
+    )
+
+
+def pytest_collection_modifyitems(config, items):
+    """
+    Modify test collection to add markers based on test location.
+    """
+    for item in items:
+        # Auto-mark tests based on their location
+        if "unit" in str(item.fspath):
+            item.add_marker(pytest.mark.unit)
+        elif "integration" in str(item.fspath):
+            item.add_marker(pytest.mark.integration)