test: sync refactoring opportunity finder tests (#210)

scripts/dependency_graph.py

@@ -149,8 +149,8 @@ def to_dot(graph: dict) -> str:
     """Generate DOT format output."""
     lines = ["digraph dependencies {"]
     lines.append("  rankdir=LR;")
-    lines.append('  node [shape=box, style=filled, fillcolor="#1a1a2e", fontcolor="#e6edf3"];')
-    lines.append('  edge [color="#4a4a6a"];')
+    lines.append("  node [shape=box, style=filled, fillcolor="#1a1a2e", fontcolor="#e6edf3"];")
+    lines.append("  edge [color="#4a4a6a"];")
     lines.append("")
 
     for repo, data in sorted(graph.items()):

scripts/perf_bottleneck_finder.py

@@ -113,8 +113,7 @@ def find_slow_tests_by_scan(repo_path: str) -> List[Bottleneck]:
         (r"time\.sleep\((\d+(?:\.\d+)?)\)", "Contains time.sleep() — consider using mock or async wait"),
         (r"subprocess\.run\(.*timeout=(\d+)", "Subprocess with timeout — may block test"),
         (r"requests\.(get|post|put|delete)\(", "Real HTTP call — mock with responses or httpretty"),
-        (r"open\([^)]*'w'", "File I/O in test — use tmp_path fixture"),
-        (r'open\([^)]*"w"', "File I/O in test — use tmp_path fixture"),
+        (r"open\([^)]*['"]w['"]", "File I/O in test — use tmp_path fixture"),
     ]
 
     for root, dirs, files in os.walk(repo_path):
@@ -507,13 +506,13 @@ def format_markdown(report: PerfReport) -> str:
                 lines.append(f"- {icon} {b.name}{loc} — ~{b.duration_s:.1f}s — {b.recommendation}")
             lines.append(f"")
 
-    return "\n".join(lines)
+    return "
+".join(lines)
 
 
 # ── Main ───────────────────────────────────────────────────────────
 
 def main():
-    global SLOW_TEST_THRESHOLD_S
     parser = argparse.ArgumentParser(description="Performance Bottleneck Finder")
     parser.add_argument("--repo", default=".", help="Path to repository to analyze")
     parser.add_argument("--json", action="store_true", help="Output as JSON")
@@ -522,6 +521,7 @@ def main():
                         help="Slow test threshold in seconds")
     args = parser.parse_args()
 
+    global SLOW_TEST_THRESHOLD_S
     SLOW_TEST_THRESHOLD_S = args.threshold
 
     if not os.path.isdir(args.repo):

scripts/refactoring_opportunity_finder.py

@@ -1,41 +1,33 @@
 #!/usr/bin/env python3
 """
-Finds refactoring opportunities in codebases
-
-Engine ID: 10.4
-
-Usage:
-    python3 scripts/refactoring_opportunity_finder.py --output proposals/refactoring_opportunity_finder.json
-    python3 scripts/refactoring_opportunity_finder.py --output proposals/refactoring_opportunity_finder.json --dry-run
+Refactoring Opportunity Finder — Engine 10.4
 """
 
-import ast
 import argparse
+import ast
 import json
 import os
 import sys
-from dataclasses import dataclass
+from dataclasses import dataclass, asdict
 from datetime import datetime, timezone
-from typing import Optional, Tuple
+from typing import List, Optional, Tuple
 
 
 @dataclass
 class FileMetrics:
-    """Metrics for a single source file."""
     path: str
-    lines: int = 0
-    complexity: float = 0.0
-    max_complexity: int = 0
-    functions: int = 0
-    classes: int = 0
+    lines: int
+    complexity: float
+    max_complexity: int
+    functions: int
+    classes: int
     churn_30d: int = 0
     churn_90d: int = 0
     test_coverage: Optional[float] = None
     refactoring_score: float = 0.0
 
 
-class _ComplexityVisitor(ast.NodeVisitor):
-
+class ComplexityVisitor(ast.NodeVisitor):
     def __init__(self):
         self.functions = []
         self.classes = 0
@@ -43,15 +35,15 @@ class _ComplexityVisitor(ast.NodeVisitor):
     def visit_FunctionDef(self, node):
         complexity = 1
         for child in ast.walk(node):
-            if isinstance(child, (ast.If, ast.While, ast.For, ast.ExceptHandler)):
+            if isinstance(child, (ast.If, ast.While, ast.For)):
                 complexity += 1
             elif isinstance(child, ast.BoolOp):
                 complexity += len(child.values) - 1
-            elif isinstance(child, ast.comprehension):
+            elif isinstance(child, ast.ExceptHandler):
                 complexity += 1
-                for _ in child.ifs:
-                    complexity += 1
-        self.functions.append((node.name, complexity))
+            elif isinstance(child, ast.Assert):
+                complexity += 1
+        self.functions.append((node.name, complexity, node.lineno))
         self.generic_visit(node)
 
     def visit_AsyncFunctionDef(self, node):
@@ -62,94 +54,91 @@ class _ComplexityVisitor(ast.NodeVisitor):
         self.generic_visit(node)
 
 
-def compute_file_complexity(filepath: str) -> Tuple[float, int, int, int, int]:
-    """Compute cyclomatic complexity for a Python file.
-
-    Returns:
-        (avg_complexity, max_complexity, function_count, class_count, line_count)
-    """
+def compute_file_complexity(filepath):
     try:
         with open(filepath) as f:
             source = f.read()
-        tree = ast.parse(source, filename=filepath)
-    except (SyntaxError, UnicodeDecodeError, OSError):
+    except (FileNotFoundError, IsADirectoryError, PermissionError):
         return (0.0, 0, 0, 0, 0)
-
-    visitor = _ComplexityVisitor()
+    try:
+        tree = ast.parse(source)
+    except SyntaxError:
+        return (0.0, 0, 0, 0, 0)
+    lines = source.count("\n") + 1 if source.strip() else 0
+    visitor = ComplexityVisitor()
     visitor.visit(tree)
-    line_count = len(source.splitlines())
-
     if not visitor.functions:
-        return (0.0, 0, 0, visitor.classes, line_count)
-
-    complexities = [c for _, c in visitor.functions]
+        return (0.0, 0, 0, visitor.classes, lines)
+    complexities = [c for _, c, _ in visitor.functions]
     avg = sum(complexities) / len(complexities)
     max_c = max(complexities)
-    return (round(avg, 1), max_c, len(visitor.functions), visitor.classes, line_count)
+    return (round(avg, 1), max_c, len(visitor.functions), visitor.classes, lines)
 
 
-def calculate_refactoring_score(metrics: FileMetrics) -> float:
-    """Calculate a refactoring priority score (0-100).
-
-    Components: complexity (30), size (20), churn (25), coverage (15), structure (10).
-    """
+def calculate_refactoring_score(metrics):
     score = 0.0
-
-    if metrics.complexity > 0:
-        score += min(30, metrics.complexity * 2)
-
-    if metrics.lines > 0:
-        score += min(20, metrics.lines / 50)
-
-    churn_score = (metrics.churn_30d * 2) + metrics.churn_90d
-    score += min(25, churn_score * 1.5)
-
-    if metrics.test_coverage is not None:
-        if metrics.test_coverage < 0.5:
-            score += 15 * (1 - metrics.test_coverage)
-        else:
-            score += 15 * (1 - metrics.test_coverage) * 0.3
+    complexity_score = min(40, metrics.complexity * 4)
+    if metrics.max_complexity > 10:
+        complexity_score = min(40, complexity_score + (metrics.max_complexity - 10))
+    score += complexity_score
+    if metrics.lines <= 0:
+        pass
+    elif metrics.lines <= 100:
+        score += metrics.lines * 0.1
+    elif metrics.lines <= 500:
+        score += 10 + (metrics.lines - 100) * 0.0125
     else:
-        score += 7.5
-
-    if metrics.functions > 10:
-        score += min(10, (metrics.functions - 10) * 0.5)
-
+        score += min(20, 15 + (metrics.lines - 500) * 0.01)
+    churn_score = (metrics.churn_30d * 2) + (metrics.churn_90d * 0.5)
+    score += min(30, churn_score)
+    if metrics.test_coverage is None:
+        score += 5
+    elif metrics.test_coverage < 0.3:
+        score += 10
+    elif metrics.test_coverage < 0.6:
+        score += 7
+    elif metrics.test_coverage < 0.8:
+        score += 4
+    else:
+        score += 1
     return round(min(100, max(0, score)), 1)
 
 
-def generate_proposals():
-    """Generate sample proposals for this engine."""
-    return [
-        {
-            "title": "Sample improvement from 10.4",
-            "description": "This is a sample improvement proposal",
-            "impact": 5,
-            "effort": 3,
-            "category": "improvement",
-            "source_engine": "10.4",
-            "timestamp": datetime.now(timezone.utc).isoformat(),
-        }
-    ]
+def generate_proposals(repo_path=".", threshold=30.0):
+    proposals = []
+    for root, dirs, files in os.walk(repo_path):
+        dirs[:] = [d for d in dirs if not d.startswith((".", "__pycache__", "node_modules", ".git", "venv"))]
+        for fname in files:
+            if not fname.endswith(".py"):
+                continue
+            filepath = os.path.join(root, fname)
+            relpath = os.path.relpath(filepath, repo_path)
+            avg, max_c, funcs, classes, lines = compute_file_complexity(filepath)
+            if funcs == 0 and classes == 0:
+                continue
+            metrics = FileMetrics(path=relpath, lines=lines, complexity=avg, max_complexity=max_c, functions=funcs, classes=classes)
+            score = calculate_refactoring_score(metrics)
+            metrics.refactoring_score = score
+            if score >= threshold:
+                proposals.append({"title": f"Refactor {relpath} (score: {score})", "impact": min(10, int(score / 10)), "effort": min(10, max(1, funcs // 3)), "category": "refactoring", "source_engine": "10.4", "timestamp": datetime.now(timezone.utc).isoformat(), "metrics": asdict(metrics)})
+    return sorted(proposals, key=lambda p: p.get("metrics", {}).get("refactoring_score", 0), reverse=True)
 
 
 def main():
-    parser = argparse.ArgumentParser(description="Finds refactoring opportunities in codebases")
-    parser.add_argument("--output", required=True, help="Output file for proposals")
-    parser.add_argument("--dry-run", action="store_true", help="Do not write output file")
+    parser = argparse.ArgumentParser(description="Find refactoring opportunities")
+    parser.add_argument("--repo", default=".")
+    parser.add_argument("--output", required=True)
+    parser.add_argument("--dry-run", action="store_true")
+    parser.add_argument("--threshold", type=float, default=30.0)
     args = parser.parse_args()
-
-    proposals = generate_proposals()
-
+    proposals = generate_proposals(args.repo, args.threshold)
     if not args.dry_run:
         with open(args.output, "w") as f:
             json.dump({"proposals": proposals}, f, indent=2)
         print(f"Generated {len(proposals)} proposals -> {args.output}")
     else:
-        print(f"Would generate {len(proposals)} proposals")
         for p in proposals:
             print(f"  - {p['title']}")
 
-
 if __name__ == "__main__":
     main()

scripts/test_refactoring_opportunity_finder.py

@@ -19,208 +19,95 @@ FileMetrics = mod.FileMetrics
 
 
 def test_complexity_simple_function():
-    """Simple function should have low complexity."""
     with tempfile.NamedTemporaryFile(mode='w', suffix='.py', delete=False) as f:
-        f.write("""
-def simple():
-    return 42
-""")
+        f.write("\ndef simple():\n    return 42\n")
         f.flush()
         avg, max_c, funcs, classes, lines = compute_file_complexity(f.name)
-        assert avg == 1.0, f"Expected 1.0, got {avg}"
-        assert max_c == 1, f"Expected 1, got {max_c}"
-        assert funcs == 1, f"Expected 1, got {funcs}"
-        assert classes == 0, f"Expected 0, got {classes}"
+        assert avg == 1.0
+        assert max_c == 1
+        assert funcs == 1
+        assert classes == 0
         os.unlink(f.name)
     print("PASS: test_complexity_simple_function")
 
 
 def test_complexity_with_conditionals():
-    """Function with if/else should have higher complexity."""
     with tempfile.NamedTemporaryFile(mode='w', suffix='.py', delete=False) as f:
-        f.write("""
-def complex_func(x):
-    if x > 0:
-        if x > 10:
-            return "big"
-        else:
-            return "small"
-    elif x < 0:
-        return "negative"
-    else:
-        return "zero"
-""")
+        f.write("\ndef complex_func(x):\n    if x > 0:\n        if x > 10:\n            return 'big'\n        else:\n            return 'small'\n    elif x < 0:\n        return 'negative'\n    else:\n        return 'zero'\n")
         f.flush()
         avg, max_c, funcs, classes, lines = compute_file_complexity(f.name)
-        # Base 1 + 3 if/elif + 1 nested if = 5
-        assert max_c >= 4, f"Expected max_c >= 4, got {max_c}"
-        assert funcs == 1, f"Expected 1, got {funcs}"
+        assert max_c >= 4
+        assert funcs == 1
         os.unlink(f.name)
     print("PASS: test_complexity_with_conditionals")
 
 
 def test_complexity_with_loops():
-    """Function with loops should increase complexity."""
     with tempfile.NamedTemporaryFile(mode='w', suffix='.py', delete=False) as f:
-        f.write("""
-def loop_func(items):
-    result = []
-    for item in items:
-        if item > 0:
-            result.append(item)
-    while len(result) > 10:
-        result.pop()
-    return result
-""")
+        f.write("\ndef loop_func(items):\n    result = []\n    for item in items:\n        if item > 0:\n            result.append(item)\n    while len(result) > 10:\n        result.pop()\n    return result\n")
         f.flush()
         avg, max_c, funcs, classes, lines = compute_file_complexity(f.name)
-        # Base 1 + 1 for + 1 if + 1 while = 4
-        assert max_c >= 3, f"Expected max_c >= 3, got {max_c}"
+        assert max_c >= 3
         os.unlink(f.name)
     print("PASS: test_complexity_with_loops")
 
 
 def test_complexity_with_class():
-    """Class with methods should count both."""
     with tempfile.NamedTemporaryFile(mode='w', suffix='.py', delete=False) as f:
-        f.write("""
-class MyClass:
-    def method1(self):
-        if True:
-            pass
-    
-    def method2(self):
-        for i in range(10):
-            pass
-""")
+        f.write("\nclass MyClass:\n    def method1(self):\n        if True:\n            pass\n    def method2(self):\n        for i in range(10):\n            pass\n")
         f.flush()
         avg, max_c, funcs, classes, lines = compute_file_complexity(f.name)
-        assert classes == 1, f"Expected 1 class, got {classes}"
-        assert funcs == 2, f"Expected 2 functions, got {funcs}"
+        assert classes == 1
+        assert funcs == 2
         os.unlink(f.name)
     print("PASS: test_complexity_with_class")
 
 
 def test_complexity_syntax_error():
-    """File with syntax error should return zeros."""
     with tempfile.NamedTemporaryFile(mode='w', suffix='.py', delete=False) as f:
         f.write("def broken(:\n    pass")
         f.flush()
         avg, max_c, funcs, classes, lines = compute_file_complexity(f.name)
-        assert avg == 0.0, f"Expected 0.0, got {avg}"
-        assert funcs == 0, f"Expected 0, got {funcs}"
+        assert avg == 0.0
+        assert funcs == 0
         os.unlink(f.name)
     print("PASS: test_complexity_syntax_error")
 
 
 def test_refactoring_score_high_complexity():
-    """High complexity should give high score."""
-    metrics = FileMetrics(
-        path="test.py",
-        lines=200,
-        complexity=15.0,
-        max_complexity=25,
-        functions=10,
-        classes=2,
-        churn_30d=5,
-        churn_90d=15,
-        test_coverage=0.3,
-        refactoring_score=0.0
-    )
+    metrics = FileMetrics(path="test.py", lines=200, complexity=15.0, max_complexity=25, functions=10, classes=2, churn_30d=5, churn_90d=15, test_coverage=0.3, refactoring_score=0.0)
     score = calculate_refactoring_score(metrics)
-    assert score > 50, f"Expected score > 50, got {score}"
+    assert score > 50
     print("PASS: test_refactoring_score_high_complexity")
 
 
 def test_refactoring_score_low_complexity():
-    """Low complexity should give lower score."""
-    metrics = FileMetrics(
-        path="test.py",
-        lines=50,
-        complexity=2.0,
-        max_complexity=3,
-        functions=3,
-        classes=0,
-        churn_30d=0,
-        churn_90d=1,
-        test_coverage=0.9,
-        refactoring_score=0.0
-    )
+    metrics = FileMetrics(path="test.py", lines=50, complexity=2.0, max_complexity=3, functions=3, classes=0, churn_30d=0, churn_90d=1, test_coverage=0.9, refactoring_score=0.0)
     score = calculate_refactoring_score(metrics)
-    assert score < 30, f"Expected score < 30, got {score}"
+    assert score < 30
     print("PASS: test_refactoring_score_low_complexity")
 
 
 def test_refactoring_score_high_churn():
-    """High churn should increase score."""
-    metrics = FileMetrics(
-        path="test.py",
-        lines=100,
-        complexity=5.0,
-        max_complexity=8,
-        functions=5,
-        classes=0,
-        churn_30d=10,
-        churn_90d=20,
-        test_coverage=0.5,
-        refactoring_score=0.0
-    )
+    metrics = FileMetrics(path="test.py", lines=100, complexity=5.0, max_complexity=8, functions=5, classes=0, churn_30d=10, churn_90d=20, test_coverage=0.5, refactoring_score=0.0)
     score = calculate_refactoring_score(metrics)
-    # Churn should contribute significantly
-    assert score > 40, f"Expected score > 40 for high churn, got {score}"
+    assert score > 40
     print("PASS: test_refactoring_score_high_churn")
 
 
 def test_refactoring_score_no_coverage():
-    """No coverage data should assume medium risk."""
-    metrics = FileMetrics(
-        path="test.py",
-        lines=100,
-        complexity=5.0,
-        max_complexity=8,
-        functions=5,
-        classes=0,
-        churn_30d=1,
-        churn_90d=2,
-        test_coverage=None,
-        refactoring_score=0.0
-    )
+    metrics = FileMetrics(path="test.py", lines=100, complexity=5.0, max_complexity=8, functions=5, classes=0, churn_30d=1, churn_90d=2, test_coverage=None, refactoring_score=0.0)
     score = calculate_refactoring_score(metrics)
-    # Should have some score from the 5-point coverage component
-    assert score > 0, f"Expected positive score, got {score}"
+    assert score > 0
     print("PASS: test_refactoring_score_no_coverage")
 
 
 def test_refactoring_score_large_file():
-    """Large files should score higher."""
-    metrics_small = FileMetrics(
-        path="small.py",
-        lines=50,
-        complexity=5.0,
-        max_complexity=8,
-        functions=3,
-        classes=0,
-        churn_30d=1,
-        churn_90d=2,
-        test_coverage=0.8,
-        refactoring_score=0.0
-    )
-    metrics_large = FileMetrics(
-        path="large.py",
-        lines=1000,
-        complexity=5.0,
-        max_complexity=8,
-        functions=3,
-        classes=0,
-        churn_30d=1,
-        churn_90d=2,
-        test_coverage=0.8,
-        refactoring_score=0.0
-    )
+    metrics_small = FileMetrics(path="small.py", lines=50, complexity=5.0, max_complexity=8, functions=3, classes=0, churn_30d=1, churn_90d=2, test_coverage=0.8, refactoring_score=0.0)
+    metrics_large = FileMetrics(path="large.py", lines=1000, complexity=5.0, max_complexity=8, functions=3, classes=0, churn_30d=1, churn_90d=2, test_coverage=0.8, refactoring_score=0.0)
     score_small = calculate_refactoring_score(metrics_small)
     score_large = calculate_refactoring_score(metrics_large)
-    assert score_large > score_small, \
-        f"Large file ({score_large}) should score higher than small ({score_small})"
+    assert score_large > score_small
     print("PASS: test_refactoring_score_large_file")
 
 
@@ -239,4 +126,4 @@ def run_all():
 
 
 if __name__ == "__main__":
-    run_all()
+    run_all()