Canonical NormalizedFinding schema with Severity enum (CRITICAL/HIGH/MEDIUM/LOW/INFO). Per-project adapters for 9 tools with severity mapping for string labels, int 1-10, float 0-1, Python Enum, and computed properties. CLI pipe interface and registry. Nightshift-Task: event-taxonomy Nightshift-Ref: https://github.com/marcus/nightshift
146 lines
3.6 KiB
Python
146 lines
3.6 KiB
Python
from event_taxonomy.adapters import (
|
|
bus_factor,
|
|
dep_risk,
|
|
doc_drift,
|
|
knowledge_silo,
|
|
perf_regression,
|
|
roadmap_entropy,
|
|
schema_evolution,
|
|
semantic_diff,
|
|
test_flakiness,
|
|
)
|
|
from event_taxonomy.schema import Severity
|
|
|
|
|
|
def test_bus_factor():
|
|
f = bus_factor.normalize({
|
|
"file": "core.py",
|
|
"top_author": "alice",
|
|
"top_author_pct": 85.0,
|
|
"num_contributors": 2,
|
|
"bus_factor": 1,
|
|
"risk_label": "CRITICAL",
|
|
})
|
|
assert f.severity == Severity.CRITICAL
|
|
assert f.file == "core.py"
|
|
assert "alice" in f.message
|
|
|
|
|
|
def test_dep_risk():
|
|
f = dep_risk.normalize({
|
|
"name": "requests",
|
|
"ecosystem": "pypi",
|
|
"version": "2.28.0",
|
|
"risk_label": "HIGH",
|
|
"vuln_count": 2,
|
|
"months_stale": 6,
|
|
})
|
|
assert f.severity == Severity.HIGH
|
|
assert "requests" in f.message
|
|
|
|
|
|
def test_doc_drift():
|
|
f = doc_drift.normalize({
|
|
"kind": "docstring_param",
|
|
"severity": "error",
|
|
"message": "Param x not in signature",
|
|
"file": "model.py",
|
|
"lineno": 42,
|
|
"symbol": "process",
|
|
})
|
|
assert f.severity == Severity.HIGH
|
|
assert f.line == 42
|
|
assert f.file == "model.py"
|
|
|
|
|
|
def test_knowledge_silo():
|
|
f = knowledge_silo.normalize({
|
|
"filepath": "auth.py",
|
|
"total_commits": 50,
|
|
"dominant_author": "bob",
|
|
"dominant_commits": 45,
|
|
"other_authors": {"alice": 5},
|
|
"risk": "HIGH",
|
|
})
|
|
assert f.severity == Severity.HIGH
|
|
assert "bob" in f.message
|
|
|
|
|
|
def test_perf_regression():
|
|
f = perf_regression.normalize({
|
|
"pattern": "n-plus-one-query",
|
|
"severity": 8,
|
|
"file": "api.py",
|
|
"line": 123,
|
|
"message": "DB call inside loop",
|
|
"snippet": "for x in items: db.query(x)",
|
|
})
|
|
assert f.severity == Severity.CRITICAL
|
|
assert f.file == "api.py"
|
|
assert f.line == 123
|
|
|
|
|
|
def test_roadmap_entropy():
|
|
f = roadmap_entropy.normalize({
|
|
"entropy_score": 0.65,
|
|
"risk_label": "high",
|
|
"base_count": 10,
|
|
"head_count": 15,
|
|
"item_count_delta": 5,
|
|
"description_churn": 0.25,
|
|
"priority_shuffles": 3,
|
|
})
|
|
assert f.severity == Severity.HIGH
|
|
assert "0.65" in f.message
|
|
|
|
|
|
def test_schema_evolution():
|
|
f = schema_evolution.normalize({
|
|
"operation": {"op_type": "drop_column", "args": ["users", "password"]},
|
|
"risk_level": "dangerous",
|
|
"rationale": "Dropping column causes data loss",
|
|
"recommendation": "Back up first",
|
|
})
|
|
assert f.severity == Severity.CRITICAL
|
|
assert f.recommendation == "Back up first"
|
|
|
|
|
|
def test_semantic_diff():
|
|
f = semantic_diff.normalize({
|
|
"path": "api.py",
|
|
"categories": ["REFACTOR", "FEATURE"],
|
|
"summary": "Modified api.py",
|
|
"added": 45,
|
|
"removed": 23,
|
|
})
|
|
assert f.severity == Severity.MEDIUM
|
|
assert f.file == "api.py"
|
|
|
|
|
|
def test_semantic_diff_large_churn():
|
|
f = semantic_diff.normalize({
|
|
"path": "big.py",
|
|
"categories": ["FEATURE"],
|
|
"summary": "Rewrote big.py",
|
|
"added": 200,
|
|
"removed": 50,
|
|
})
|
|
assert f.severity == Severity.HIGH
|
|
|
|
|
|
def test_test_flakiness():
|
|
f = test_flakiness.normalize({
|
|
"test_id": "tests.integration::test_auth",
|
|
"classname": "tests.integration",
|
|
"total_runs": 20,
|
|
"pass_count": 12,
|
|
"fail_count": 8,
|
|
"error_count": 0,
|
|
"skip_count": 0,
|
|
"flakiness_rate": 0.4,
|
|
"avg_duration": 1.25,
|
|
"duration_stddev": 0.35,
|
|
})
|
|
assert f.severity == Severity.HIGH
|
|
assert "40%" in f.message
|