redswitch/fix_all_html.py at master · Redswitch-Ai/redswitch · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
#!/usr/bin/env python3
"""Fix encoding issues in all RedSwitch HTML files."""
import os

def fix_file(filepath):
    print(f"Processing: {filepath}")

    with open(filepath, 'rb') as f:
        content = f.read()

    original = content

    # Fix double-encoded UTF-8 sequences (bytes level)
    fixes = [
        # Em dash variants
        (b'\xc3\xa2\xe2\x82\xac\xe2\x80\x9d', b'-'),
        (b'\xc3\xa2\xe2\x82\xac\xe2\x80\x9c', b'-'),
        (b'\xc3\xa2\xe2\x82\xac\xe2\x80\x99', b'-'),
        (b'\xc3\xa2\xe2\x82\xac\xc2\x94', b'-'),
        (b'\xc3\xa2\xc2\x80\xc2\x94', b'-'),
        (b'\xe2\x80\x94', b'-'),  # proper em dash -> hyphen for simplicity

        # Bullet
        (b'\xc3\xa2\xe2\x82\xac\xc2\xa2', b'-'),
        (b'\xc3\xa2\xc2\x80\xc2\xa2', b'-'),
        (b'\xe2\x80\xa2', b'-'),

        # Checkmark - fix corrupted to proper
        (b'\xc3\xa2\xc5\x93\xe2\x80\x9c', b'\xe2\x9c\x93'),
        (b'\xc3\xa2\xc2\x9c\xe2\x80\x9c', b'\xe2\x9c\x93'),
        (b'\xc3\xa2\xc2\x9c\xc2\x93', b'\xe2\x9c\x93'),

        # Arrow
        (b'\xc3\xa2\xe2\x80\xa0\xe2\x80\x99', b'\xe2\x86\x92'),
        (b'\xc3\xa2\xc2\x86\xc2\x92', b'\xe2\x86\x92'),

        # Timer/stopwatch emoji - various corruptions
        (b'\xc3\xa2\xc2\x8f\xc2\xb1\xc3\xaf', b'\xe2\x8f\xb1\xef\xb8\x8f'),
        (b'\xc3\xa2\xc2\xb1\xc3\xaf', b'\xe2\x8f\xb1\xef\xb8\x8f'),

        # Money emoji
        (b'\xc3\xb0\xc5\xb8\xe2\x80\x99\xc2\xb8', b'\xf0\x9f\x92\xb8'),
        (b'\xc3\xb0\xc2\x9f\xc2\x92\xc2\xb8', b'\xf0\x9f\x92\xb8'),

        # Zombie emoji
        (b'\xc3\xb0\xc5\xb8\xc2\xa7\xc5\xb8', b'\xf0\x9f\xa7\x9f'),
        (b'\xc3\xb0\xc2\x9f\xc2\xa7\xc2\x9f', b'\xf0\x9f\xa7\x9f'),

        # Robot emoji
        (b'\xc3\xb0\xc5\xb8\xc2\xa4\xe2\x80\x93', b'\xf0\x9f\xa4\x96'),
        (b'\xc3\xb0\xc2\x9f\xc2\xa4\xc2\x96', b'\xf0\x9f\xa4\x96'),

        # Siren emoji
        (b'\xc3\xb0\xc5\xb8\xc5\xa1\xc2\xa8', b'\xf0\x9f\x9a\xa8'),
        (b'\xc3\xb0\xc2\x9f\xc2\x9a\xc2\xa8', b'\xf0\x9f\x9a\xa8'),

        # Right single quote -> apostrophe
        (b'\xc3\xa2\xe2\x82\xac\xe2\x84\xa2', b"'"),
        (b'\xe2\x80\x99', b"'"),

        # Left/right double quotes -> straight quotes
        (b'\xe2\x80\x9c', b'"'),
        (b'\xe2\x80\x9d', b'"'),
    ]

    for old, new in fixes:
        if old in content:
            content = content.replace(old, new)
            print(f"  Fixed: {old[:20]}...")

    if content != original:
        with open(filepath, 'wb') as f:
            f.write(content)
        print(f"  -> Saved!")
        return True
    else:
        print(f"  -> No changes needed")
        return False

# Process all HTML files
fixed_count = 0
for root, dirs, files in os.walk('.'):
    # Skip backup files
    if 'backup' in root.lower() or 'old' in root.lower():
        continue
    for filename in files:
        if filename.endswith('.html') and 'old' not in filename.lower() and 'backup' not in filename.lower():
            filepath = os.path.join(root, filename)
            if fix_file(filepath):
                fixed_count += 1

print(f"\nTotal files fixed: {fixed_count}")