fix_encoding.py

#!/usr/bin/env python3
import os

def fix_file(filepath):
    print(f"Processing: {filepath}")
    with open(filepath, 'r', encoding='utf-8') as f:
        content = f.read()
    
    original = content
    
    # Fix double-encoded UTF-8 sequences
    # Each corrupted sequence and its replacement (using ASCII when sensible)
    fixes = [
        # Em dash variants
        ('\u00e2\u20ac\u201d', '-'),
        ('\u00e2\u20ac\u201c', '-'),
        ('\u00e2\u20ac\u0153', '-'),
        # Bullet
        ('\u00e2\u20ac\u00a2', '-'),
        # Right single quote
        ('\u00e2\u20ac\u2122', "'"),
        # Arrow
        ('\u00e2\u2020\u2019', '->'),
        # Check mark
        ('\u00e2\u0178\u201c', 'X'),
        # Money emoji
        ('\u00f0\u0178\u2019\u00b8', '$'),
        # Zombie emoji
        ('\u00f0\u0178\u00a7\u0178', 'Z'),
        # Family emoji
        ('\u00f0\u0178\u2019\u00a8\u00e2\u20ac\u00a0\u00f0\u0178\u2019\u00a9\u00e2\u20ac\u00a0\u00f0\u0178\u2019\u00a7', 'FAM'),
        # Robot emoji
        ('\u00f0\u0178\u00a4\u2013', 'BOT'),
        # Siren emoji
        ('\u00f0\u0178\u0161\u00a8', '!'),
        # Email emoji
        ('\u00f0\u0178\u201c\u00a7', '@'),
        # Timer emoji
        ('\u00e2\u00b1\u00ef\u00b8\u008f', 'T'),
    ]
    
    for bad, good in fixes:
        content = content.replace(bad, good)
    
    if content != original:
        with open(filepath, 'w', encoding='utf-8') as f:
            f.write(content)
        print(f"  -> Fixed!")
        return True
    else:
        print(f"  -> No changes needed")
        return False

for root, dirs, files in os.walk('.'):
    for filename in files:
        if filename.endswith('.html'):
            fix_file(os.path.join(root, filename))

print("Done!")