Find files with zeroes inside, that occupy less space than they should

file_with_holes.py

#!/usr/bin/python3

import os, sys

def find_sparse_files(start_path, top_n=50):
    results = []
    
    for dirpath, _, filenames in os.walk(start_path):
        for f in filenames:
            fp = os.path.join(dirpath, f)
            if os.path.islink(fp):
                continue
                
            try:
                stat = os.stat(fp)
                apparent_size = stat.st_size
                # Linux allocates disk usage in st_blocks (512-byte increments)
                occupied_size = stat.st_blocks * 512
                
                hole_size = apparent_size - occupied_size
                
                if hole_size > 0:
                    results.append((hole_size, fp))
            except OSError:
                continue # Skip unreadable files safely

    # Sort descending by hole size
    results.sort(key=lambda x: x[0], reverse=True)
    
    if results:
        # Print header
        print(f"{'Hole Size':<12} | {'File Path'}")
        print("-" * 60)
        
        for hole, path in results[:top_n]:
            print(f"{format_size(hole):<12} | {path}")
    else:
        print("No holes in files")

def format_size(bytes_size):
    for unit in ['B', 'KB', 'MB', 'GB', 'TB', 'PB']:
        if bytes_size < 1024:
            return f"{bytes_size:.2f} {unit}"
        bytes_size /= 1024
    return f"{bytes_size:.2f} EB"

if __name__ == '__main__':
    target_dir = sys.argv[1] if len(sys.argv) > 1 else '.'
    print(f"Scanning '{target_dir}' for large unallocated spans...")
    find_sparse_files(target_dir)