Automatically Detect Corrupted Files Using SHA-256 Checksums in Python

import hashlib
import os

def compute_sha256(filepath: str) -> str:
    """Compute SHA-256 checksum of a file."""
    sha256 = hashlib.sha256()
    with open(filepath, 'rb') as f:
        for chunk in iter(lambda: f.read(4096), b''):
            sha256.update(chunk)
    return sha256.hexdigest()

def validate_file_integrity(filepath: str, expected_checksum: str) -> bool:
    """Check if file's checksum matches expected."""
    return compute_sha256(filepath) == expected_checksum

# Example: create a test file, compute its checksum, then detect corruption
test_file = "demo.txt"
with open(test_file, "w") as f:
    f.write("Hello, world! This is a test file.")

original_checksum = compute_sha256(test_file)
print(f"Original checksum: {original_checksum}")

# Simulate corruption: append extra data
with open(test_file, "a") as f:
    f.write("CORRUPTED")

is_corrupted = not validate_file_integrity(test_file, original_checksum)
print(f"File corrupted: {is_corrupted}")

# Cleanup
os.remove(test_file)