feat: Set up Python testing infrastructure with Poetry and pytest

.gitignore

@@ -0,0 +1,161 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+.python-version
+
+# pipenv
+Pipfile.lock
+
+# poetry
+# Do not ignore poetry.lock - it should be committed
+# poetry.lock
+
+# pdm
+.pdm.toml
+.pdm-python
+.pdm-build/
+
+# PEP 582
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# IDEs
+.vscode/
+.idea/
+*.swp
+*.swo
+*~
+
+# Claude settings
+.claude/*
+
+# OS files
+.DS_Store
+Thumbs.db
+
+# Redis dump files
+dump.rdb
+
+# Temporary files
+*.tmp
+*.temp
+*.bak

pyproject.toml

@@ -0,0 +1,85 @@
+[tool.poetry]
+name = "event-monitor"
+version = "0.1.0"
+description = "Event monitoring system using Scrapy and Redis"
+authors = ["Your Name <you@example.com>"]
+readme = "README.md"
+packages = [{include = "EventMonitor"}]
+
+[tool.poetry.dependencies]
+python = "^3.8"
+scrapy = "^2.11.0"
+redis = "^5.0.1"
+lxml = "^4.9.3"
+
+[tool.poetry.group.dev.dependencies]
+pytest = "^7.4.3"
+pytest-cov = "^4.1.0"
+pytest-mock = "^3.12.0"
+
+[tool.poetry.scripts]
+test = "pytest:main"
+tests = "pytest:main"
+
+[tool.pytest.ini_options]
+minversion = "7.0"
+testpaths = ["tests"]
+python_files = ["test_*.py", "*_test.py"]
+python_classes = ["Test*"]
+python_functions = ["test_*"]
+addopts = [
+    "-v",
+    "--strict-markers",
+    "--strict-config",
+    "--cov=EventMonitor",
+    "--cov=collect_person_rel",
+    "--cov-branch",
+    "--cov-report=term-missing:skip-covered",
+    "--cov-report=html:htmlcov",
+    "--cov-report=xml:coverage.xml",
+    "--cov-fail-under=0",
+]
+markers = [
+    "unit: Unit tests",
+    "integration: Integration tests",
+    "slow: Slow tests",
+]
+
+[tool.coverage.run]
+source = ["EventMonitor", "collect_person_rel"]
+branch = true
+omit = [
+    "*/tests/*",
+    "*/test_*",
+    "*/__pycache__/*",
+    "*/venv/*",
+    "*/virtualenv/*",
+    "*/.venv/*",
+    "*/setup.py",
+]
+
+[tool.coverage.report]
+exclude_lines = [
+    "pragma: no cover",
+    "def __repr__",
+    "if self.debug:",
+    "if __name__ == .__main__.:",
+    "raise AssertionError",
+    "raise NotImplementedError",
+    "if 0:",
+    "if False:",
+    "import",
+    "pass",
+]
+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"

tests/conftest.py

@@ -0,0 +1,144 @@
+import os
+import sys
+import tempfile
+import shutil
+from pathlib import Path
+from unittest.mock import Mock, MagicMock
+
+import pytest
+import redis
+from scrapy.http import TextResponse, Request
+
+sys.path.insert(0, os.path.abspath(os.path.join(os.path.dirname(__file__), '..')))
+
+
+@pytest.fixture
+def temp_dir():
+    """Create a temporary directory for testing."""
+    temp_path = tempfile.mkdtemp()
+    yield Path(temp_path)
+    shutil.rmtree(temp_path)
+
+
+@pytest.fixture
+def mock_redis_connection():
+    """Mock Redis connection for testing."""
+    mock_pool = Mock()
+    mock_conn = MagicMock()
+
+    mock_conn.sadd.return_value = 1
+    mock_conn.spop.return_value = "test_data###value1###value2###value3"
+    mock_conn.get.return_value = "test_value"
+    mock_conn.set.return_value = True
+
+    return mock_conn
+
+
+@pytest.fixture
+def mock_redis_pool(monkeypatch, mock_redis_connection):
+    """Mock Redis connection pool."""
+    def mock_connection_pool(*args, **kwargs):
+        return Mock()
+
+    def mock_redis(*args, **kwargs):
+        return mock_redis_connection
+
+    monkeypatch.setattr(redis, "ConnectionPool", mock_connection_pool)
+    monkeypatch.setattr(redis, "Redis", mock_redis)
+
+    return mock_redis_connection
+
+
+@pytest.fixture
+def sample_rel_data(temp_dir):
+    """Create sample relation data file for testing."""
+    rel_file = temp_dir / "rel_data.txt"
+    content = """person1###relation1###person2###type1
+person3###relation2###person4###type2
+person5###relation3###person6###type3
+"""
+    rel_file.write_text(content)
+    return rel_file
+
+
+@pytest.fixture
+def sample_person_data(temp_dir):
+    """Create sample person data file for testing."""
+    person_file = temp_dir / "person.txt"
+    content = """张三
+李四
+王五
+"""
+    person_file.write_text(content)
+    return person_file
+
+
+@pytest.fixture
+def scrapy_response():
+    """Create a mock Scrapy response for testing."""
+    def _create_response(url="http://test.com", body="<html><body>Test content</body></html>", 
+                        status=200, headers=None):
+        request = Request(url)
+        return TextResponse(
+            url=url,
+            request=request,
+            body=body.encode('utf-8'),
+            status=status,
+            headers=headers or {}
+        )
+    return _create_response
+
+
+@pytest.fixture
+def mock_scrapy_settings():
+    """Mock Scrapy settings for testing."""
+    return {
+        'BOT_NAME': 'test_bot',
+        'SPIDER_MODULES': ['EventMonitor.spiders'],
+        'NEWSPIDER_MODULE': 'EventMonitor.spiders',
+        'ROBOTSTXT_OBEY': True,
+        'CONCURRENT_REQUESTS': 16,
+        'DOWNLOAD_DELAY': 0,
+    }
+
+
+@pytest.fixture
+def mock_news_parser():
+    """Mock news parser for testing."""
+    parser = Mock()
+    parser.extract_content.return_value = {
+        'title': 'Test News Title',
+        'content': 'Test news content',
+        'date': '2024-01-01',
+        'source': 'Test Source'
+    }
+    return parser
+
+
+@pytest.fixture
+def sample_html_content():
+    """Sample HTML content for testing."""
+    return """
+    <html>
+        <head><title>Test Page</title></head>
+        <body>
+            <h1>Test Article</h1>
+            <div class="content">
+                <p>This is test content about person1 and person2.</p>
+                <p>They have some relation in this news.</p>
+            </div>
+            <div class="date">2024-01-01</div>
+        </body>
+    </html>
+    """
+
+
+@pytest.fixture(autouse=True)
+def reset_sys_modules():
+    """Reset sys.modules to avoid import issues between tests."""
+    modules_snapshot = sys.modules.copy()
+    yield
+    for module in list(sys.modules.keys()):
+        if module.startswith('EventMonitor') and module in sys.modules:
+            del sys.modules[module]
+    sys.modules.update(modules_snapshot)