spark: py_stats.py - quick Python file analyzer with AST parsing

wizard-work/spark/output.txt

@@ -0,0 +1,7 @@
+Python File Statistics for: /root/.hermes/profiles/spark/
+==================================================
+Total .py files: 50
+Total lines: 11590
+Total imports: 434
+Total functions: 415
+Total classes: 10

wizard-work/spark/py_stats.py

@@ -0,0 +1,107 @@
+#!/usr/bin/env python3
+"""Quick Python file statistics reporter.
+Usage: python py_stats.py <directory> [output_file]
+Reports: number of .py files, total lines, imports, functions, classes.
+"""
+import os
+import sys
+import ast
+from pathlib import Path
+
+def analyze_py_file(filepath):
+    """Analyze a single Python file."""
+    result = {
+        'lines': 0,
+        'imports': 0,
+        'functions': 0,
+        'classes': 0
+    }
+    
+    try:
+        with open(filepath, 'r', encoding='utf-8') as f:
+            content = f.read()
+            result['lines'] = len(content.splitlines())
+            
+        tree = ast.parse(content)
+        for node in ast.walk(tree):
+            if isinstance(node, (ast.Import, ast.ImportFrom)):
+                result['imports'] += 1
+            elif isinstance(node, (ast.FunctionDef, ast.AsyncFunctionDef)):
+                result['functions'] += 1
+            elif isinstance(node, ast.ClassDef):
+                result['classes'] += 1
+    except Exception as e:
+        result['error'] = str(e)
+    
+    return result
+
+def scan_directory(directory):
+    """Scan directory for Python files and report statistics."""
+    stats = {
+        'files': 0,
+        'total_lines': 0,
+        'total_imports': 0,
+        'total_functions': 0,
+        'total_classes': 0,
+        'file_details': []
+    }
+    
+    for root, dirs, files in os.walk(directory):
+        # Skip hidden directories and common non-source folders
+        dirs[:] = [d for d in dirs if not d.startswith('.') and d not in ('__pycache__', 'venv', '.venv', 'node_modules')]
+        
+        for file in files:
+            if file.endswith('.py'):
+                filepath = os.path.join(root, file)
+                relpath = os.path.relpath(filepath, directory)
+                fstats = analyze_py_file(filepath)
+                fstats['path'] = relpath
+                stats['file_details'].append(fstats)
+                stats['files'] += 1
+                stats['total_lines'] += fstats['lines']
+                stats['total_imports'] += fstats['imports']
+                stats['total_functions'] += fstats['functions']
+                stats['total_classes'] += fstats['classes']
+    
+    return stats
+
+def main():
+    if len(sys.argv) < 2:
+        print("Usage: python py_stats.py <directory> [output_file]")
+        sys.exit(1)
+    
+    directory = sys.argv[1]
+    output_file = sys.argv[2] if len(sys.argv) > 2 else None
+    
+    if not os.path.isdir(directory):
+        print(f"Error: {directory} is not a directory")
+        sys.exit(1)
+    
+    stats = scan_directory(directory)
+    
+    output = []
+    output.append(f"Python File Statistics for: {directory}")
+    output.append("=" * 50)
+    output.append(f"Total .py files: {stats['files']}")
+    output.append(f"Total lines: {stats['total_lines']}")
+    output.append(f"Total imports: {stats['total_imports']}")
+    output.append(f"Total functions: {stats['total_functions']}")
+    output.append(f"Total classes: {stats['total_classes']}")
+    output.append("")
+    
+    if stats['files'] <= 20:  # Show details for small projects
+        output.append("File details:")
+        output.append("-" * 50)
+        for f in stats['file_details']:
+            output.append(f"  {f['path']}: {f['lines']} lines, {f['imports']} imports, {f['functions']} funcs, {f['classes']} classes")
+    
+    result = "\n".join(output)
+    print(result)
+    
+    if output_file:
+        with open(output_file, 'w') as f:
+            f.write(result)
+        print(f"\nResults written to: {output_file}")
+
+if __name__ == '__main__':
+    main()