Initial commit

tests/conftest.py

@@ -0,0 +1,340 @@
+"""Pytest configuration and shared fixtures for coverage tests."""
+
+# FILE: tests/conftest.py
+
+import asyncio
+import os
+import tempfile
+from datetime import datetime
+from pathlib import Path
+from unittest.mock import AsyncMock, MagicMock
+
+import pytest
+import yaml
+
+from libs.schemas import (
+    CompiledCoveragePolicy,
+    ConflictRules,
+    CoveragePolicy,
+    Defaults,
+    EvidenceItem,
+    Privacy,
+    QuestionTemplates,
+    Role,
+    SchedulePolicy,
+    StatusClassifier,
+    StatusClassifierConfig,
+    TaxYearBoundary,
+    Trigger,
+)
+
+# pylint: disable=wrong-import-position,import-error,too-few-public-methods,global-statement
+# pylint: disable=raise-missing-from,unused-argument,too-many-arguments,too-many-positional-arguments
+# pylint: disable=too-many-locals,import-outside-toplevel
+# mypy: disable-error-code=union-attr
+# mypy: disable-error-code=no-untyped-def
+
+
+@pytest.fixture(scope="session")
+def event_loop():
+    """Create an instance of the default event loop for the test session."""
+    loop = asyncio.get_event_loop_policy().new_event_loop()
+    yield loop
+    loop.close()
+
+
+@pytest.fixture
+def temp_config_dir():
+    """Create temporary config directory with test policy files"""
+    with tempfile.TemporaryDirectory() as temp_dir:
+        config_dir = Path(temp_dir)
+
+        # Create baseline policy
+        baseline_policy = {
+            "version": "1.0",
+            "jurisdiction": "UK",
+            "tax_year": "2024-25",
+            "tax_year_boundary": {"start": "2024-04-06", "end": "2025-04-05"},
+            "defaults": {
+                "confidence_thresholds": {"ocr": 0.82, "extract": 0.85},
+                "date_tolerance_days": 30,
+            },
+            "document_kinds": ["P60", "P11D", "P45"],
+            "triggers": {
+                "SA102": {"any_of": ["exists(IncomeItem[type='Employment'])"]},
+                "SA105": {"any_of": ["exists(IncomeItem[type='UKPropertyRent'])"]},
+            },
+            "schedules": {
+                "SA102": {
+                    "evidence": [
+                        {
+                            "id": "P60",
+                            "role": "REQUIRED",
+                            "boxes": ["SA102_b1", "SA102_b2"],
+                            "acceptable_alternatives": ["P45", "FinalPayslipYTD"],
+                        },
+                        {
+                            "id": "P11D",
+                            "role": "CONDITIONALLY_REQUIRED",
+                            "condition": "exists(BenefitInKind=true)",
+                            "boxes": ["SA102_b9"],
+                        },
+                    ]
+                },
+                "SA105": {
+                    "evidence": [
+                        {
+                            "id": "LettingAgentStatements",
+                            "role": "REQUIRED",
+                            "boxes": ["SA105_b5"],
+                        }
+                    ]
+                },
+            },
+            "status_classifier": {
+                "present_verified": {
+                    "min_ocr": 0.82,
+                    "min_extract": 0.85,
+                    "date_in_year": True,
+                },
+                "present_unverified": {
+                    "min_ocr": 0.60,
+                    "min_extract": 0.70,
+                    "date_in_year_or_tolerance": True,
+                },
+                "conflicting": {"conflict_rules": ["Same doc kind, different totals"]},
+                "missing": {"default": True},
+            },
+            "conflict_resolution": {"precedence": ["P60", "P11D"]},
+            "question_templates": {
+                "default": {
+                    "text": "To complete the {schedule} for {tax_year}, we need {evidence}.",
+                    "why": "{why}. See guidance: {guidance_doc}.",
+                }
+            },
+            "privacy": {"vector_pii_free": True, "redact_patterns": []},
+        }
+
+        with open(config_dir / "coverage.yaml", "w") as f:
+            yaml.dump(baseline_policy, f)
+
+        yield config_dir
+
+
+@pytest.fixture
+def sample_policy():
+    """Create sample compiled policy for testing"""
+    policy = CoveragePolicy(
+        version="1.0",
+        jurisdiction="UK",
+        tax_year="2024-25",
+        tax_year_boundary=TaxYearBoundary(start="2024-04-06", end="2025-04-05"),
+        defaults=Defaults(
+            confidence_thresholds={"ocr": 0.82, "extract": 0.85},
+            date_tolerance_days=30,
+        ),
+        document_kinds=["P60", "P11D"],
+        triggers={"SA102": Trigger(any_of=["exists(IncomeItem[type='Employment'])"])},
+        schedules={
+            "SA102": SchedulePolicy(
+                evidence=[
+                    EvidenceItem(
+                        id="P60",
+                        role=Role.REQUIRED,
+                        boxes=["SA102_b1", "SA102_b2"],
+                        acceptable_alternatives=["P45", "FinalPayslipYTD"],
+                    )
+                ]
+            )
+        },
+        status_classifier=StatusClassifierConfig(
+            present_verified=StatusClassifier(min_ocr=0.82, min_extract=0.85),
+            present_unverified=StatusClassifier(min_ocr=0.60, min_extract=0.70),
+            conflicting=StatusClassifier(conflict_rules=[]),
+            missing=StatusClassifier(conflict_rules=[]),
+        ),
+        conflict_resolution=ConflictRules(precedence=["P60"]),
+        question_templates=QuestionTemplates(default={"text": "test", "why": "test"}),
+        privacy=Privacy(vector_pii_free=True, redact_patterns=[]),
+    )
+
+    # Create compiled policy with mock predicates
+    compiled = CompiledCoveragePolicy(
+        policy=policy,
+        compiled_predicates={
+            "exists(IncomeItem[type='Employment'])": lambda tid, ty: True
+        },
+        compiled_at=datetime.utcnow(),
+        hash="test-hash",
+        source_files=["test.yaml"],
+    )
+
+    return compiled
+
+
+@pytest.fixture
+def mock_kg_client():
+    """Create mock KG client for testing"""
+    client = AsyncMock()
+
+    # Default successful evidence finding
+    client.run_query = AsyncMock(
+        return_value=[
+            {
+                "doc_id": "DOC-P60-001",
+                "kind": "P60",
+                "page": 1,
+                "bbox": {"x": 100, "y": 200, "width": 300, "height": 50},
+                "ocr_confidence": 0.95,
+                "extract_confidence": 0.92,
+                "date": "2024-05-15",
+            }
+        ]
+    )
+
+    return client
+
+
+@pytest.fixture
+def mock_rag_client():
+    """Create mock RAG client for testing"""
+    client = AsyncMock()
+
+    # Default citation search results
+    client.search = AsyncMock(
+        return_value=[
+            {
+                "doc_id": "SA102-Notes-2025",
+                "locator": "p.3 §1.1",
+                "url": "https://docs.local/SA102-Notes-2025#p3s1.1",
+            }
+        ]
+    )
+
+    return client
+
+
+@pytest.fixture
+def mock_db_session():
+    """Create mock database session for testing"""
+    session = AsyncMock()
+
+    # Mock database operations
+    session.add = MagicMock()
+    session.commit = AsyncMock()
+    session.rollback = AsyncMock()
+    session.close = AsyncMock()
+
+    return session
+
+
+@pytest.fixture
+def mock_policy_loader():
+    """Create mock policy loader for testing"""
+    loader = MagicMock()
+
+    # Mock policy loading
+    loader.load_policy = MagicMock()
+    loader.compile_predicates = MagicMock()
+    loader.validate_policy = MagicMock()
+
+    return loader
+
+
+@pytest.fixture(autouse=True)
+def setup_test_environment():
+    """Set up test environment variables"""
+    original_env = os.environ.copy()
+
+    # Set test environment variables
+    os.environ.update(
+        {
+            "ENVIRONMENT": "test",
+            "CONFIG_DIR": "/tmp/test-config",
+            "NEO4J_URI": "bolt://localhost:7687",
+            "NEO4J_USER": "neo4j",
+            "NEO4J_PASSWORD": "testpass",
+            "POSTGRES_URL": "postgresql://postgres:postgres@localhost:5432/test_db",
+            "QDRANT_URL": "http://localhost:6333",
+            "VAULT_URL": "http://localhost:8200",
+            "VAULT_TOKEN": "test-token",
+        }
+    )
+
+    yield
+
+    # Restore original environment
+    os.environ.clear()
+    os.environ.update(original_env)
+
+
+@pytest.fixture
+def sample_evidence_data():
+    """Sample evidence data for testing"""
+    return [
+        {
+            "doc_id": "DOC-P60-001",
+            "kind": "P60",
+            "page": 1,
+            "bbox": {"x": 100, "y": 200, "width": 300, "height": 50},
+            "ocr_confidence": 0.95,
+            "extract_confidence": 0.92,
+            "date": "2024-05-15T10:00:00Z",
+        },
+        {
+            "doc_id": "DOC-P11D-001",
+            "kind": "P11D",
+            "page": 1,
+            "bbox": {"x": 50, "y": 100, "width": 400, "height": 60},
+            "ocr_confidence": 0.88,
+            "extract_confidence": 0.90,
+            "date": "2024-07-06T14:30:00Z",
+        },
+    ]
+
+
+@pytest.fixture
+def sample_citation_data():
+    """Sample citation data for testing"""
+    return [
+        {
+            "rule_id": "UK.SA102.P60.Required",
+            "doc_id": "SA102-Notes-2025",
+            "locator": "p.3 §1.1",
+            "url": "https://docs.local/SA102-Notes-2025#p3s1.1",
+        },
+        {
+            "rule_id": "UK.SA102.P11D.Conditional",
+            "doc_id": "SA102-Notes-2025",
+            "locator": "p.5 §2.3",
+            "url": "https://docs.local/SA102-Notes-2025#p5s2.3",
+        },
+    ]
+
+
+# Pytest markers for test categorization
+pytest_plugins: list[str] = []
+
+
+def pytest_configure(config):
+    """Configure pytest markers"""
+    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", "e2e: mark test as an end-to-end test")
+    config.addinivalue_line("markers", "slow: mark test as slow running")
+
+
+def pytest_collection_modifyitems(config, items):
+    """Automatically mark tests based on their location"""
+    for item in items:
+        # Mark tests based on directory structure
+        if "unit" in str(item.fspath):
+            item.add_marker(pytest.mark.unit)
+        elif "integration" in str(item.fspath):
+            item.add_marker(pytest.mark.integration)
+        elif "e2e" in str(item.fspath):
+            item.add_marker(pytest.mark.e2e)
+
+        # Mark async tests
+        if asyncio.iscoroutinefunction(item.function):
+            item.add_marker(pytest.mark.asyncio)