Files
wehub-resource-sync 7a0da7932b
OSV-Scanner (Scheduled) / scan-scheduled (push) Failing after 0s
Create Release / test-gate (push) Has been cancelled
Create Release / release-gate (push) Has been cancelled
Create Release / ci-gate (push) Has been cancelled
Create Release / version-check (push) Has been cancelled
Create Release / e2e-test-gate (push) Has been cancelled
Create Release / responsive-test-gate (push) Has been cancelled
Create Release / compat-test-gate (push) Has been cancelled
Create Release / compose-integration-gate (push) Has been cancelled
Create Release / vulture-gate (push) Has been cancelled
Create Release / build (push) Has been cancelled
Create Release / provenance (push) Has been cancelled
Create Release / prerelease-docker (push) Has been cancelled
Create Release / publish-docker (push) Has been cancelled
Create Release / create-release (push) Has been cancelled
Create Release / cleanup-changelog (push) Has been cancelled
Create Release / trigger-pypi (push) Has been cancelled
Create Release / monitor-pypi (push) Has been cancelled
Create Release / Clean up orphan prerelease tags and signatures (push) Has been cancelled
Docker Tests (Consolidated) / UI Tests (Puppeteer) [research-form] (push) Has been cancelled
Docker Tests (Consolidated) / UI Tests (Puppeteer) [research-metrics] (push) Has been cancelled
Docker Tests (Consolidated) / UI Tests (Puppeteer) [research-workflow] (push) Has been cancelled
Docker Tests (Consolidated) / UI Tests (Puppeteer) [settings-core] (push) Has been cancelled
CodeQL Advanced / Analyze (javascript-typescript) (push) Has been cancelled
Docker Tests (Consolidated) / UI Tests (Puppeteer) [history-news] (push) Has been cancelled
Docker Tests (Consolidated) / UI Tests (Puppeteer) [library] (push) Has been cancelled
Docker Tests (Consolidated) / UI Tests (Puppeteer) [link-analytics] (push) Has been cancelled
Docker Tests (Consolidated) / UI Tests (Puppeteer) [chat-core] (push) Has been cancelled
Docker Tests (Consolidated) / UI Tests (Puppeteer) [chat-lifecycle] (push) Has been cancelled
Docker Tests (Consolidated) / UI Tests (Puppeteer) [error-benchmark] (push) Has been cancelled
Docker Tests (Consolidated) / UI Tests (Puppeteer) [settings-pages] (push) Has been cancelled
Docker Tests (Consolidated) / UI Tests (Puppeteer) (push) Has been cancelled
Docker Tests (Consolidated) / Accessibility Tests (push) Has been cancelled
Docker Tests (Consolidated) / LLM Unit Tests (push) Has been cancelled
Docker Tests (Consolidated) / LLM Example Tests (push) Has been cancelled
Docker Tests (Consolidated) / Production Image Smoke Test (push) Has been cancelled
Docker Tests (Consolidated) / Infrastructure Tests (push) Has been cancelled
OSSF Scorecard / OSSF Security Scorecard Analysis (push) Has been cancelled
Docker Tests (Consolidated) / UI Tests (Puppeteer) [mobile] (push) Has been cancelled
Backwards Compatibility / Verify Encryption Constants (push) Has been cancelled
Backwards Compatibility / PyPI Version Compatibility (push) Has been cancelled
Backwards Compatibility / Database Migration Tests (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Docker Tests (Consolidated) / detect-changes (push) Has been cancelled
Docker Tests (Consolidated) / Build Test Image (push) Has been cancelled
Docker Tests (Consolidated) / All Pytest Tests + Coverage (push) Has been cancelled
Docker Tests (Consolidated) / UI Tests (Puppeteer) [accessibility] (push) Has been cancelled
Docker Tests (Consolidated) / UI Tests (Puppeteer) [api-crud] (push) Has been cancelled
Docker Tests (Consolidated) / UI Tests (Puppeteer) [auth-login] (push) Has been cancelled
Docker Tests (Consolidated) / UI Tests (Puppeteer) [auth-pages] (push) Has been cancelled
Docker Tests (Consolidated) / UI Tests (Puppeteer) [auth-register] (push) Has been cancelled
chore: import upstream snapshot with attribution
2026-07-13 13:08:55 +08:00

381 lines
13 KiB
Python

"""
Comprehensive tests for domain_classifier/classifier.py
Tests cover:
- DomainClassifier initialization
- Domain categories
- Classification logic
- LLM integration
"""
import pytest
from unittest.mock import Mock, patch, MagicMock
class TestDomainCategories:
"""Tests for domain category definitions."""
def test_domain_categories_exist(self):
"""Test that domain categories are defined."""
from local_deep_research.domain_classifier.classifier import (
DOMAIN_CATEGORIES,
)
assert isinstance(DOMAIN_CATEGORIES, dict)
assert len(DOMAIN_CATEGORIES) > 0
def test_expected_categories_present(self):
"""Test that expected top-level categories exist."""
from local_deep_research.domain_classifier.classifier import (
DOMAIN_CATEGORIES,
)
expected_categories = [
"Academic & Research",
"News & Media",
"Reference & Documentation",
"Social & Community",
"Business & Commerce",
"Technology",
"Government & Organization",
"Other",
]
for category in expected_categories:
assert category in DOMAIN_CATEGORIES, (
f"Missing category: {category}"
)
def test_academic_subcategories(self):
"""Test academic category subcategories."""
from local_deep_research.domain_classifier.classifier import (
DOMAIN_CATEGORIES,
)
academic = DOMAIN_CATEGORIES.get("Academic & Research", [])
assert "University/Education" in academic
assert "Scientific Journal" in academic
assert "Research Institution" in academic
def test_news_subcategories(self):
"""Test news category subcategories."""
from local_deep_research.domain_classifier.classifier import (
DOMAIN_CATEGORIES,
)
news = DOMAIN_CATEGORIES.get("News & Media", [])
assert "General News" in news
assert "Tech News" in news
assert "Business News" in news
def test_technology_subcategories(self):
"""Test technology category subcategories."""
from local_deep_research.domain_classifier.classifier import (
DOMAIN_CATEGORIES,
)
tech = DOMAIN_CATEGORIES.get("Technology", [])
assert "Software Development" in tech
assert "Open Source Project" in tech
assert "Cloud Service" in tech
def test_other_includes_unknown(self):
"""Test that Other category includes Unknown."""
from local_deep_research.domain_classifier.classifier import (
DOMAIN_CATEGORIES,
)
other = DOMAIN_CATEGORIES.get("Other", [])
assert "Unknown" in other
def test_all_categories_have_subcategories(self):
"""Test that all categories have at least one subcategory."""
from local_deep_research.domain_classifier.classifier import (
DOMAIN_CATEGORIES,
)
for category, subcategories in DOMAIN_CATEGORIES.items():
assert len(subcategories) > 0, (
f"Category {category} has no subcategories"
)
class TestDomainClassifierInit:
"""Tests for DomainClassifier initialization."""
def test_init_with_username(self):
"""Test initialization with username."""
from local_deep_research.domain_classifier.classifier import (
DomainClassifier,
)
classifier = DomainClassifier(username="testuser")
assert classifier.username == "testuser"
assert classifier.settings_snapshot is None
assert classifier.llm is None
def test_init_with_settings_snapshot(self):
"""Test initialization with settings snapshot."""
from local_deep_research.domain_classifier.classifier import (
DomainClassifier,
)
snapshot = {"llm.model": "test-model"}
classifier = DomainClassifier(
username="testuser", settings_snapshot=snapshot
)
assert classifier.settings_snapshot == snapshot
@patch("local_deep_research.domain_classifier.classifier.get_llm")
def test_get_llm_creates_instance(self, mock_get_llm):
"""Test that _get_llm creates LLM instance."""
from local_deep_research.domain_classifier.classifier import (
DomainClassifier,
)
mock_llm = Mock()
mock_get_llm.return_value = mock_llm
classifier = DomainClassifier(username="testuser")
result = classifier._get_llm()
assert result == mock_llm
mock_get_llm.assert_called_once()
@patch("local_deep_research.domain_classifier.classifier.get_llm")
def test_get_llm_caches_instance(self, mock_get_llm):
"""Test that _get_llm caches LLM instance."""
from local_deep_research.domain_classifier.classifier import (
DomainClassifier,
)
mock_llm = Mock()
mock_get_llm.return_value = mock_llm
classifier = DomainClassifier(username="testuser")
result1 = classifier._get_llm()
result2 = classifier._get_llm()
assert result1 == result2
# Should only be called once due to caching
assert mock_get_llm.call_count == 1
class TestDomainClassifierClassify:
"""Tests for classification functionality."""
@pytest.fixture
def classifier(self):
"""Create a DomainClassifier instance for testing."""
from local_deep_research.domain_classifier.classifier import (
DomainClassifier,
)
return DomainClassifier(username="testuser")
@patch(
"local_deep_research.domain_classifier.classifier.get_user_db_session"
)
@patch("local_deep_research.domain_classifier.classifier.get_llm")
def test_classify_domain_success(
self, mock_get_llm, mock_get_db_session, classifier
):
"""Test successful domain classification."""
mock_llm = MagicMock()
mock_response = Mock()
mock_response.content = """
{
"category": "Technology",
"subcategory": "Software Development",
"confidence": 0.9,
"reasoning": "Domain is a software project"
}
"""
mock_llm.invoke.return_value = mock_response
mock_get_llm.return_value = mock_llm
# Mock the database session context manager
mock_session = MagicMock()
mock_session.__enter__ = Mock(return_value=mock_session)
mock_session.__exit__ = Mock(return_value=False)
# No existing classification
mock_session.query.return_value.filter_by.return_value.first.return_value = None
mock_get_db_session.return_value = mock_session
result = classifier.classify_domain("github.com")
assert result is not None
@patch(
"local_deep_research.domain_classifier.classifier.get_user_db_session"
)
@patch("local_deep_research.domain_classifier.classifier.get_llm")
def test_classify_domain_handles_invalid_json(
self, mock_get_llm, mock_get_db_session, classifier
):
"""Test handling of invalid JSON response from LLM."""
mock_llm = MagicMock()
mock_response = Mock()
mock_response.content = "Not valid JSON"
mock_llm.invoke.return_value = mock_response
mock_get_llm.return_value = mock_llm
mock_session = MagicMock()
mock_session.__enter__ = Mock(return_value=mock_session)
mock_session.__exit__ = Mock(return_value=False)
mock_session.query.return_value.filter_by.return_value.first.return_value = None
mock_get_db_session.return_value = mock_session
# Invalid JSON from the LLM raises ValueError inside the session
# context, which the SUT's broad `except Exception` catches and
# converts to a None return. (See classifier.py:225-265.)
result = classifier.classify_domain("example.com")
assert result is None
@patch(
"local_deep_research.domain_classifier.classifier.get_user_db_session"
)
@patch("local_deep_research.domain_classifier.classifier.get_llm")
def test_classify_domain_handles_llm_error(
self, mock_get_llm, mock_get_db_session, classifier
):
"""Test handling of LLM errors during classification."""
mock_llm = MagicMock()
mock_llm.invoke.side_effect = Exception("LLM error")
mock_get_llm.return_value = mock_llm
mock_session = MagicMock()
mock_session.__enter__ = Mock(return_value=mock_session)
mock_session.__exit__ = Mock(return_value=False)
mock_session.query.return_value.filter_by.return_value.first.return_value = None
mock_get_db_session.return_value = mock_session
# Should handle error gracefully
result = classifier.classify_domain("example.com")
# Should return Unknown or None on error
assert result is None or (
hasattr(result, "category") and "Unknown" in str(result.category)
)
@patch(
"local_deep_research.domain_classifier.classifier.get_user_db_session"
)
def test_classify_domain_empty_domain(
self, mock_get_db_session, classifier
):
"""Empty-string domain must not crash; the SUT routes through the
LLM path (no cached row), and with no LLM mock configured the
broad except in classify_domain converts the error to a None
return."""
mock_session = MagicMock()
mock_session.__enter__ = Mock(return_value=mock_session)
mock_session.__exit__ = Mock(return_value=False)
mock_session.query.return_value.filter_by.return_value.first.return_value = None
mock_get_db_session.return_value = mock_session
result = classifier.classify_domain("")
assert result is None
@patch(
"local_deep_research.domain_classifier.classifier.get_user_db_session"
)
def test_classify_domain_none_domain(self, mock_get_db_session, classifier):
"""Same path as the empty-string case: no cached row, no LLM mock,
broad except → None return."""
mock_session = MagicMock()
mock_session.__enter__ = Mock(return_value=mock_session)
mock_session.__exit__ = Mock(return_value=False)
mock_session.query.return_value.filter_by.return_value.first.return_value = None
mock_get_db_session.return_value = mock_session
result = classifier.classify_domain(None)
assert result is None
class TestClassifyAllDomains:
"""Tests for batch/all-domain classification functionality."""
def test_classify_all_domains_method_exists(self):
"""Test that classify_all_domains method exists."""
from local_deep_research.domain_classifier.classifier import (
DomainClassifier,
)
classifier = DomainClassifier(username="testuser")
assert hasattr(classifier, "classify_all_domains")
assert callable(classifier.classify_all_domains)
class TestCategoryValidation:
"""Tests for category validation."""
def test_all_subcategories_are_strings(self):
"""Test that all subcategories are strings."""
from local_deep_research.domain_classifier.classifier import (
DOMAIN_CATEGORIES,
)
for category, subcategories in DOMAIN_CATEGORIES.items():
for subcat in subcategories:
assert isinstance(subcat, str), (
f"Subcategory in {category} is not a string: {subcat}"
)
def test_no_duplicate_subcategories_within_category(self):
"""Test that there are no duplicate subcategories within a category."""
from local_deep_research.domain_classifier.classifier import (
DOMAIN_CATEGORIES,
)
for category, subcategories in DOMAIN_CATEGORIES.items():
unique_subcats = set(subcategories)
assert len(unique_subcats) == len(subcategories), (
f"Duplicate subcategories in {category}"
)
class TestUrlparseExceptionInClassifyAll:
"""Tests for urlparse exception handling in classify_all_domains (PR #2027).
PR #2027 changed bare `except:` to `except Exception:` when
parsing URLs to extract domains.
"""
def test_valid_url_extracts_domain(self):
"""Valid URL extracts domain correctly."""
from urllib.parse import urlparse
url = "https://www.example.com/path"
parsed = urlparse(url)
domain = parsed.netloc.lower()
if domain.startswith("www."):
domain = domain[4:]
assert domain == "example.com"
def test_url_without_scheme_no_netloc(self):
"""URL without scheme has no netloc."""
from urllib.parse import urlparse
url = "just-some-text"
parsed = urlparse(url)
domain = parsed.netloc.lower()
assert domain == ""
def test_empty_url_handled(self):
"""Empty URL string produces empty domain."""
from urllib.parse import urlparse
url = ""
parsed = urlparse(url)
domain = parsed.netloc.lower()
assert domain == ""