feat: implement compute_file_complexity, FileMetrics, calculate_refactoring_score (#210)

scripts/perf_bottleneck_finder.py

@@ -113,7 +113,8 @@ 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):
@@ -506,13 +507,13 @@ def format_markdown(report: PerfReport) -> str:
                 lines.append(f"- {icon} {b.name}{loc} — ~{b.duration_s:.1f}s — {b.recommendation}")
             lines.append(f"")
 
-    return "
-".join(lines)
+    return "\n".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")
@@ -521,7 +522,6 @@ 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

@@ -9,24 +9,126 @@ Usage:
     python3 scripts/refactoring_opportunity_finder.py --output proposals/refactoring_opportunity_finder.json --dry-run
 """
 
+import ast
 import argparse
 import json
+import os
 import sys
+from dataclasses import dataclass
 from datetime import datetime, timezone
+from typing import 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
+    churn_30d: int = 0
+    churn_90d: int = 0
+    test_coverage: Optional[float] = None
+    refactoring_score: float = 0.0
+
+
+class _ComplexityVisitor(ast.NodeVisitor):
+
+    def __init__(self):
+        self.functions = []
+        self.classes = 0
+
+    def visit_FunctionDef(self, node):
+        complexity = 1
+        for child in ast.walk(node):
+            if isinstance(child, (ast.If, ast.While, ast.For, ast.ExceptHandler)):
+                complexity += 1
+            elif isinstance(child, ast.BoolOp):
+                complexity += len(child.values) - 1
+            elif isinstance(child, ast.comprehension):
+                complexity += 1
+                for _ in child.ifs:
+                    complexity += 1
+        self.functions.append((node.name, complexity))
+        self.generic_visit(node)
+
+    def visit_AsyncFunctionDef(self, node):
+        self.visit_FunctionDef(node)
+
+    def visit_ClassDef(self, node):
+        self.classes += 1
+        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)
+    """
+    try:
+        with open(filepath) as f:
+            source = f.read()
+        tree = ast.parse(source, filename=filepath)
+    except (SyntaxError, UnicodeDecodeError, OSError):
+        return (0.0, 0, 0, 0, 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]
+    avg = sum(complexities) / len(complexities)
+    max_c = max(complexities)
+    return (round(avg, 1), max_c, len(visitor.functions), visitor.classes, line_count)
+
+
+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).
+    """
+    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
+    else:
+        score += 7.5
+
+    if metrics.functions > 10:
+        score += min(10, (metrics.functions - 10) * 0.5)
+
+    return round(min(100, max(0, score)), 1)
 
 
 def generate_proposals():
     """Generate sample proposals for this engine."""
-    # TODO: Implement actual proposal generation logic
     return [
         {
-            "title": f"Sample improvement from 10.4",
+            "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()
+            "timestamp": datetime.now(timezone.utc).isoformat(),
         }
     ]
 
@@ -34,12 +136,11 @@ def generate_proposals():
 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="Don't write output file")
-    
+    parser.add_argument("--dry-run", action="store_true", help="Do not write output file")
     args = parser.parse_args()
-    
+
     proposals = generate_proposals()
-    
+
     if not args.dry_run:
         with open(args.output, "w") as f:
             json.dump({"proposals": proposals}, f, indent=2)