fe517158a0
Some checks failed
Test / pytest (pull_request) Failing after 29s
- Introduce scripts/test_documentation_generator.py: scans test files, adds module docstrings (explaining what is tested) and function docstrings (explaining verification purpose) without altering logic. - Applies documentation to 11 previously-undocumented test files: * tests/test_ci_config.py — added module-level docstring * tests/test_dedup.py — 30 function docstrings * tests/test_knowledge_gap_identifier.py — 10 function docstrings * tests/test_perf_bottleneck_finder.py — 25 function docstrings * tests/test_quality_gate.py — 14 function docstrings * scripts/test_diff_analyzer.py — 10 function docstrings * scripts/test_gitea_issue_parser.py — 6 function docstrings * scripts/test_harvest_prompt_comprehensive.py — 5 function docstrings * scripts/test_improvement_proposals.py — 2 function docstrings * scripts/test_knowledge_staleness.py — 8 function docstrings * scripts/test_session_pair_harvester.py — 5 function docstrings - Idempotent: re-running detects all 19 test files as up-to-date. - Processes up to 25 files per run (meets 20+ capacity requirement). Closes #88
123 lines
4.3 KiB
Python
123 lines
4.3 KiB
Python
"""
|
|
Tests for quality_gate.py — Knowledge entry quality scoring.
|
|
"""
|
|
|
|
import unittest
|
|
from datetime import datetime, timezone, timedelta
|
|
|
|
import sys
|
|
from pathlib import Path
|
|
sys.path.insert(0, str(Path(__file__).parent.parent))
|
|
|
|
from quality_gate import (
|
|
score_specificity,
|
|
score_actionability,
|
|
score_freshness,
|
|
score_source_quality,
|
|
score_entry,
|
|
filter_entries,
|
|
)
|
|
|
|
|
|
class TestScoreSpecificity(unittest.TestCase):
|
|
def test_specific_content_scores_high(self):
|
|
"""Verifies specific content scores high logic."""
|
|
content = "Run `python3 deploy.py --env prod` on 2026-04-15. Example: step 1 configure nginx."
|
|
score = score_specificity(content)
|
|
self.assertGreater(score, 0.6)
|
|
|
|
def test_vague_content_scores_low(self):
|
|
"""Verifies vague content scores low logic."""
|
|
content = "It generally depends. Various factors might affect this. Basically, it varies."
|
|
score = score_specificity(content)
|
|
self.assertLess(score, 0.5)
|
|
|
|
def test_empty_scores_baseline(self):
|
|
"""Verifies behavior with empty or None input."""
|
|
score = score_specificity("")
|
|
self.assertAlmostEqual(score, 0.5, delta=0.1)
|
|
|
|
|
|
class TestScoreActionability(unittest.TestCase):
|
|
def test_actionable_content_scores_high(self):
|
|
"""Verifies actionable content scores high logic."""
|
|
content = "1. Run `pip install -r requirements.txt`\n2. Execute `python3 train.py`\n3. Verify with `pytest`"
|
|
score = score_actionability(content)
|
|
self.assertGreater(score, 0.6)
|
|
|
|
def test_abstract_content_scores_low(self):
|
|
"""Verifies abstract content scores low logic."""
|
|
content = "The concept of intelligence is fascinating and multifaceted."
|
|
score = score_actionability(content)
|
|
self.assertLess(score, 0.5)
|
|
|
|
|
|
class TestScoreFreshness(unittest.TestCase):
|
|
def test_recent_timestamp_scores_high(self):
|
|
"""Verifies recent timestamp scores high logic."""
|
|
recent = datetime.now(timezone.utc).isoformat()
|
|
score = score_freshness(recent)
|
|
self.assertGreater(score, 0.9)
|
|
|
|
def test_old_timestamp_scores_low(self):
|
|
"""Verifies old timestamp scores low logic."""
|
|
old = (datetime.now(timezone.utc) - timedelta(days=365)).isoformat()
|
|
score = score_freshness(old)
|
|
self.assertLess(score, 0.2)
|
|
|
|
def test_none_returns_baseline(self):
|
|
"""Verifies behavior with empty or None input."""
|
|
score = score_freshness(None)
|
|
self.assertEqual(score, 0.5)
|
|
|
|
|
|
class TestScoreSourceQuality(unittest.TestCase):
|
|
def test_claude_scores_high(self):
|
|
"""Verifies claude scores high logic."""
|
|
self.assertGreater(score_source_quality("claude-sonnet"), 0.85)
|
|
|
|
def test_ollama_scores_lower(self):
|
|
"""Verifies ollama scores lower logic."""
|
|
self.assertLess(score_source_quality("ollama"), 0.7)
|
|
|
|
def test_unknown_returns_default(self):
|
|
"""Verifies unknown returns default logic."""
|
|
self.assertEqual(score_source_quality("unknown"), 0.5)
|
|
|
|
|
|
class TestScoreEntry(unittest.TestCase):
|
|
def test_good_entry_scores_high(self):
|
|
"""Verifies good entry scores high logic."""
|
|
entry = {
|
|
"content": "To deploy: run `kubectl apply -f deployment.yaml`. Verify with `kubectl get pods`.",
|
|
"model": "claude-sonnet",
|
|
"timestamp": datetime.now(timezone.utc).isoformat(),
|
|
}
|
|
score = score_entry(entry)
|
|
self.assertGreater(score, 0.6)
|
|
|
|
def test_poor_entry_scores_low(self):
|
|
"""Verifies poor entry scores low logic."""
|
|
entry = {
|
|
"content": "It depends. Various things might happen.",
|
|
"model": "unknown",
|
|
}
|
|
score = score_entry(entry)
|
|
self.assertLess(score, 0.5)
|
|
|
|
|
|
class TestFilterEntries(unittest.TestCase):
|
|
def test_filters_low_quality(self):
|
|
"""Verifies knowledge filtering by filters low quality."""
|
|
entries = [
|
|
{"content": "Run `deploy.py` to fix the issue.", "model": "claude"},
|
|
{"content": "It might work sometimes.", "model": "unknown"},
|
|
{"content": "Configure nginx: step 1 edit nginx.conf", "model": "gpt-4"},
|
|
]
|
|
filtered = filter_entries(entries, threshold=0.5)
|
|
self.assertGreaterEqual(len(filtered), 2)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
unittest.main()
|