feat: Set up comprehensive Python testing infrastructure with Poetry

.gitignore

@@ -171,4 +171,16 @@ dmypy.json
 *.pdf
 /*.sh
 /*.py
-local_json_data/
+local_json_data/
+
+# Claude
+.claude/*
+
+# Poetry
+# Do not ignore poetry.lock - it should be committed
+dist/
+.pytest_cache/
+htmlcov/
+coverage.xml
+.coverage
+.coverage.*

code/__init__.py

@@ -0,0 +1 @@
+"""ICCV 2023 Paper Analysis code package."""

pyproject.toml

@@ -0,0 +1,86 @@
+[tool.poetry]
+name = "iccv2023-paper-analysis"
+version = "0.1.0"
+description = "ICCV 2023 Paper Analysis Project"
+authors = ["Your Name <[email protected]>"]
+readme = "README.md"
+packages = [{include = "code"}]
+
+[tool.poetry.dependencies]
+python = "^3.8"
+beautifulsoup4 = "^4.12.0"
+markdown2 = "^2.4.0"
+prettytable = "^3.9.0"
+PyGithub = "^2.1.0"
+
+[tool.poetry.group.dev.dependencies]
+pytest = "^8.0.0"
+pytest-cov = "^5.0.0"
+pytest-mock = "^3.12.0"
+
+[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 = [
+    "--strict-markers",
+    "--verbose",
+    "-ra",
+    "--cov=code",
+    "--cov-report=term-missing:skip-covered",
+    "--cov-report=html",
+    "--cov-report=xml",
+    "--cov-fail-under=0",  # Set to 0 for infrastructure setup, change to 80 when adding real tests
+]
+markers = [
+    "unit: Unit tests",
+    "integration: Integration tests",
+    "slow: Slow running tests",
+]
+filterwarnings = [
+    "error",
+    "ignore::UserWarning",
+    "ignore::DeprecationWarning",
+]
+
+[tool.coverage.run]
+source = ["code"]
+omit = [
+    "*/tests/*",
+    "*/__pycache__/*",
+    "*/venv/*",
+    "*/.venv/*",
+    "*/site-packages/*",
+]
+
+[tool.coverage.report]
+exclude_lines = [
+    "pragma: no cover",
+    "def __repr__",
+    "if self.debug:",
+    "if __name__ == .__main__.:",
+    "raise AssertionError",
+    "raise NotImplementedError",
+    "if 0:",
+    "if False:",
+    "pass",
+]
+show_missing = true
+precision = 2
+fail_under = 0  # Set to 0 for infrastructure setup, change to 80 when adding real tests
+
+[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 +1,157 @@
+"""Shared pytest fixtures and configuration."""
+
+import json
+import tempfile
+from pathlib import Path
+from unittest.mock import Mock
+
+import pytest
+
+
+@pytest.fixture
+def temp_dir():
+    """Create a temporary directory for test files."""
+    with tempfile.TemporaryDirectory() as tmpdir:
+        yield Path(tmpdir)
+
+
+@pytest.fixture
+def sample_markdown_content():
+    """Sample markdown content for testing."""
+    return """# Recognition: Detection
+
+## Main Conference
+
+| Title | Links | Paper | Video |
+|-------|-------|-------|-------|
+| [Sample Paper Title](https://example.com/paper) | [![GitHub](https://img.shields.io/badge/GitHub-Repository-blue)](https://github.com/user/repo) | [![thecvf](https://img.shields.io/badge/pdf-thecvf-green)](https://example.com/paper.pdf) | [![YouTube](https://img.shields.io/badge/YouTube-Video-red)](https://youtube.com/watch?v=123) |
+"""
+
+
+@pytest.fixture
+def sample_json_data():
+    """Sample JSON data structure for testing."""
+    return [
+        {
+            "title": "Sample Paper Title",
+            "base_url": "https://example.com",
+            "title_page": "/paper",
+            "ieee_id": None,
+            "github": "user/repo",
+            "web_page": None,
+            "github_page": None,
+            "colab": None,
+            "modelscope": None,
+            "gitee": None,
+            "gitlab": None,
+            "zenodo": None,
+            "kaggle": None,
+            "demo_page": None,
+            "paper_thecvf": "/paper.pdf",
+            "paper_arxiv_id": None,
+            "paper_pdf": None,
+            "paper_hal_science": None,
+            "paper_researchgate": None,
+            "paper_amazon": None,
+            "youtube_id": "123",
+            "drive_google": None,
+            "dropbox": None,
+            "onedrive": None,
+            "loom": None,
+            "section": "Recognition: Detection"
+        }
+    ]
+
+
+@pytest.fixture
+def mock_config(monkeypatch):
+    """Mock configuration values for testing."""
+    monkeypatch.setenv("GITHUB_REPOSITORY", "test-owner/test-repo")
+    monkeypatch.setenv("GITHUB_TOKEN", "test-token")
+    monkeypatch.setenv("GITHUB_WORKSPACE", "/test/workspace")
+
+    class MockConfig:
+        GITHUB_TOKEN = "test-token"
+        GITHUB_WORKSPACE = "/test/workspace"
+        MARKDOWN_DIRECTORY = "sections"
+        OUTPUT_DIRECTORY = "json_data"
+        MARKDOWN_DIRECTORY_LOCAL = Path("./sections").resolve()
+        OUTPUT_DIRECTORY_LOCAL = Path("./local_json_data").resolve()
+        REPO_OWNER = "test-owner"
+        REPO_NAME = "test-repo"
+        COMMIT_MESSAGE = "Update files"
+
+    return MockConfig
+
+
+@pytest.fixture
+def mock_github_repo():
+    """Mock GitHub repository for testing."""
+    mock_repo = Mock()
+    mock_repo.default_branch = "main"
+    mock_repo.get_branch.return_value.commit.sha = "abc123"
+    mock_repo.get_git_commit.return_value.tree.sha = "tree123"
+    mock_repo.create_git_tree.return_value.sha = "newtree123"
+    mock_repo.create_git_commit.return_value.sha = "newcommit123"
+    return mock_repo
+
+
+@pytest.fixture
+def sample_html_content():
+    """Sample HTML content for testing BeautifulSoup parsing."""
+    return """
+    <h2>Recognition: Detection</h2>
+    <table>
+        <tr>
+            <th>Title</th>
+            <th>Links</th>
+            <th>Paper</th>
+            <th>Video</th>
+        </tr>
+        <tr>
+            <td><a href="/paper">Sample Paper Title</a></td>
+            <td>
+                <a href="https://github.com/user/repo">
+                    <img alt="GitHub" src="github.png">
+                </a>
+            </td>
+            <td>
+                <a href="/paper.pdf">
+                    <img alt="thecvf" src="pdf.png">
+                </a>
+            </td>
+            <td>
+                <a href="https://youtube.com/watch?v=123">
+                    <img alt="Video" src="video.png">
+                </a>
+            </td>
+        </tr>
+    </table>
+    """
+
+
+@pytest.fixture
+def create_test_file(temp_dir):
+    """Factory fixture to create test files."""
+    def _create_file(filename, content):
+        file_path = temp_dir / filename
+        file_path.parent.mkdir(parents=True, exist_ok=True)
+        file_path.write_text(content)
+        return file_path
+    return _create_file
+
+
+@pytest.fixture
+def mock_beautiful_soup(monkeypatch):
+    """Mock BeautifulSoup for testing without actual HTML parsing."""
+    def mock_init(self, *args, **kwargs):
+        pass
+
+    monkeypatch.setattr("bs4.BeautifulSoup.__init__", mock_init)
+
+
+@pytest.fixture
+def capture_logs(caplog):
+    """Capture log messages during tests."""
+    with caplog.at_level("INFO"):
+        yield caplog

tests/test_infrastructure_validation.py

@@ -0,0 +1,102 @@
+"""Validation tests to verify the testing infrastructure is properly set up."""
+
+import json
+from pathlib import Path
+
+import pytest
+
+
+class TestInfrastructureValidation:
+    """Test class to validate the testing infrastructure setup."""
+
+    def test_pytest_is_working(self):
+        """Basic test to verify pytest is working."""
+        assert True
+        assert 1 + 1 == 2
+
+    def test_fixtures_are_available(self, temp_dir, sample_markdown_content):
+        """Test that fixtures from conftest.py are accessible."""
+        assert isinstance(temp_dir, Path)
+        assert temp_dir.exists()
+        assert isinstance(sample_markdown_content, str)
+        assert "Recognition: Detection" in sample_markdown_content
+
+    def test_temp_dir_fixture_creates_directory(self, temp_dir):
+        """Test that temp_dir fixture creates a working directory."""
+        test_file = temp_dir / "test.txt"
+        test_file.write_text("Hello, testing!")
+
+        assert test_file.exists()
+        assert test_file.read_text() == "Hello, testing!"
+
+    def test_create_test_file_fixture(self, create_test_file):
+        """Test the create_test_file factory fixture."""
+        test_file = create_test_file("subdir/test.json", '{"key": "value"}')
+
+        assert test_file.exists()
+        assert test_file.parent.name == "subdir"
+
+        data = json.loads(test_file.read_text())
+        assert data == {"key": "value"}
+
+    @pytest.mark.unit
+    def test_unit_marker(self):
+        """Test that unit test marker is working."""
+        assert True
+
+    @pytest.mark.integration
+    def test_integration_marker(self):
+        """Test that integration test marker is working."""
+        assert True
+
+    @pytest.mark.slow
+    def test_slow_marker(self):
+        """Test that slow test marker is working."""
+        assert True
+
+    def test_mock_fixtures_available(self, mock_config, mock_github_repo):
+        """Test that mock fixtures are available and working."""
+        assert mock_config.GITHUB_TOKEN == "test-token"
+        assert mock_config.REPO_OWNER == "test-owner"
+        assert mock_github_repo.default_branch == "main"
+
+    def test_sample_json_data_fixture(self, sample_json_data):
+        """Test the sample JSON data fixture."""
+        assert isinstance(sample_json_data, list)
+        assert len(sample_json_data) == 1
+        assert sample_json_data[0]["title"] == "Sample Paper Title"
+        assert sample_json_data[0]["github"] == "user/repo"
+
+    def test_coverage_is_tracked(self):
+        """Test that code coverage is being tracked."""
+        # This test ensures coverage reporting works
+        def dummy_function(x):
+            if x > 0:
+                return x * 2
+            else:
+                return 0
+
+        assert dummy_function(5) == 10
+        assert dummy_function(-1) == 0
+
+    def test_pytest_mock_is_available(self, mocker):
+        """Test that pytest-mock is installed and working."""
+        mock_func = mocker.Mock(return_value=42)
+        assert mock_func() == 42
+        mock_func.assert_called_once()
+
+    def test_parameterized_tests(self):
+        """Test that pytest parametrization works."""
+
+        @pytest.mark.parametrize("input_val,expected", [
+            (1, 2),
+            (2, 4),
+            (3, 6),
+        ])
+        def inner_test(input_val, expected):
+            assert input_val * 2 == expected
+
+        # Run the parameterized test
+        inner_test(1, 2)
+        inner_test(2, 4)
+        inner_test(3, 6)