spark: file extension disk usage analyzer utility

wizard-work/spark/file_ext_analyzer.py

@@ -0,0 +1,103 @@
+#!/usr/bin/env python3
+"""
+File Extension Disk Usage Analyzer
+
+Analyzes a directory and reports disk usage by file extension.
+Useful for identifying large file types in project directories.
+"""
+
+import os
+import sys
+from collections import defaultdict
+from pathlib import Path
+
+
+def analyze_directory(directory: str, extension: str = None) -> dict:
+    """
+    Analyze a directory and return file sizes grouped by extension.
+
+    Args:
+        directory: Path to directory to analyze
+        extension: Optional specific extension to filter (e.g., '.py')
+
+    Returns:
+        Dictionary mapping extensions to total size in bytes and file count
+    """
+    stats = defaultdict(lambda: {"size": 0, "count": 0})
+    dir_path = Path(directory)
+
+    if not dir_path.exists():
+        raise FileNotFoundError(f"Directory not found: {directory}")
+
+    if not dir_path.is_dir():
+        raise NotADirectoryError(f"Not a directory: {directory}")
+
+    for root, dirs, files in os.walk(dir_path):
+        # Skip hidden directories and common ignore patterns
+        dirs[:] = [d for d in dirs if not d.startswith('.') and d not in ('__pycache__', 'node_modules', '.git')]
+
+        for filename in files:
+            if filename.startswith('.'):
+                continue
+
+            filepath = Path(root) / filename
+            try:
+                size = filepath.stat().st_size
+            except OSError:
+                continue
+
+            file_ext = filepath.suffix.lower() or '(no extension)'
+
+            if extension and file_ext != extension.lower():
+                continue
+
+            stats[file_ext]["size"] += size
+            stats[file_ext]["count"] += 1
+
+    # Sort by total size descending
+    return dict(sorted(stats.items(), key=lambda x: x[1]["size"], reverse=True))
+
+
+def format_size(size_bytes: int) -> str:
+    """Format bytes to human readable string."""
+    for unit in ['B', 'KB', 'MB', 'GB', 'TB']:
+        if size_bytes < 1024.0:
+            return f"{size_bytes:.2f} {unit}"
+        size_bytes /= 1024.0
+    return f"{size_bytes:.2f} PB"
+
+
+def main():
+    if len(sys.argv) < 2:
+        print("Usage: file_ext_analyzer.py <directory> [extension]")
+        print("Example: file_ext_analyzer.py /path/to/project .py")
+        sys.exit(1)
+
+    directory = sys.argv[1]
+    extension = sys.argv[2] if len(sys.argv) > 2 else None
+
+    try:
+        stats = analyze_directory(directory, extension)
+
+        if not stats:
+            print("No files found.")
+            sys.exit(0)
+
+        print(f"\nDisk Usage Analysis: {directory}")
+        print("-" * 50)
+
+        for ext, data in stats.items():
+            print(f"{ext:15} {format_size(data['size']):>12} ({data['count']:>5} files)")
+
+        total_size = sum(d["size"] for d in stats.values())
+        total_files = sum(d["count"] for d in stats.values())
+        print("-" * 50)
+        print(f"{'TOTAL':15} {format_size(total_size):>12} ({total_files:>5} files)")
+
+    except (FileNotFoundError, NotADirectoryError) as e:
+        print(f"Error: {e}", file=sys.stderr)
+        sys.exit(1)
+
+
+if __name__ == "__main__":
+    main()