Hugging Face's logo

ACLASCollege
/
aegis-graph

Model card Files
xet
 Community
aegis-graph
File size: 1,626 Bytes
05a5750
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
import os

filepath = r'd:\aicoding\kaiyuan\v2\index.html'
with open(filepath, 'r', encoding='latin-1') as f:
    content = f.read()

# Fix common Latin-1 corruptions of UTF-8 strings
mapping = {
    '🇺🇸': '🇺🇸',
    '🇭🇰': '🇭🇰',
    '🇪🇸': '🇪🇸',
    '🇫🇷': '🇫🇷',
    '🇩🇪': '🇩🇪',
    '🇯🇵': '🇯🇵',
    '🇰🇷': '🇰🇷',
    '🇸🇦': '🇸🇦',
    '🇵🇹': '🇵🇹',
    '🌎': '🌍',
    '📢': '📢',
    '🌠': '🌍',
    '📠': '📄',
    'â–?': '▾',
    'Français': 'Français',
    'Español': 'Español',
    'Português': 'Português',
    '日本èª?': '日本語',
    '한국ì–?': '한국어',
    'ç¹ é«”ä¸­æ–‡': '繁體中文',
    'العربية': 'العربية',
    'â€?': '—',
    '•': '•',
    '©': '©'
}

# Also ensure meta charset is present
if '<meta charset="UTF-8">' not in content:
    content = content.replace('<html lang="en">', '<html lang="en">\n<head>\n    <meta charset="UTF-8">')

for old, new in mapping.items():
    content = content.replace(old, new)

# One more pass for specific broken tags seen in view_file
content = content.replace('日本èª?/option>', '日本語</option>')
content = content.replace('한국ì–?/option>', '한국어</option>')

with open(filepath, 'w', encoding='utf-8', newline='\n') as f:
    f.write(content)

print('index.html encoding and characters fixed successfully')