Spaces:
Sleeping
Sleeping
Download src/gaia/utils/fix_encoding.py from jm-vis/Final_Assignment_GAIAAgent: direct link, hf CLI and curl.
- Browser
- Download file 2.65 kB
-
https://huggingface.co/spaces/jm-vis/Final_Assignment_GAIAAgent/resolve/main/src/gaia/utils/fix_encoding.py
- Command line
-
hf download hf://spaces/jm-vis/Final_Assignment_GAIAAgent/src/gaia/utils/fix_encoding.py
-
curl -L -o fix_encoding.py https://huggingface.co/spaces/jm-vis/Final_Assignment_GAIAAgent/resolve/main/src/gaia/utils/fix_encoding.py
2.65 kB
| """ | |
| Script to find and fix Unicode characters in app.py | |
| """ | |
| import re | |
| import os | |
| def find_unicode_chars(file_path): | |
| try: | |
| with open(file_path, 'r', encoding='utf-8') as f: | |
| content = f.read() | |
| # Find all non-ASCII characters | |
| unicode_chars = set(re.findall(r'[^\x00-\x7F]', content)) | |
| if unicode_chars: | |
| print(f"Found {len(unicode_chars)} Unicode characters in {file_path}:") | |
| for char in unicode_chars: | |
| print(f" '{char}' (U+{ord(char):04X})") | |
| return unicode_chars | |
| else: | |
| print(f"No Unicode characters found in {file_path}") | |
| return None | |
| except Exception as e: | |
| print(f"Error reading {file_path}: {e}") | |
| return None | |
| def replace_unicode_chars(file_path, output_path): | |
| try: | |
| with open(file_path, 'r', encoding='utf-8') as f: | |
| content = f.read() | |
| # Replace common Unicode characters with ASCII alternatives | |
| replacements = { | |
| '✓': '[PASS]', | |
| '✗': '[FAIL]', | |
| '❌': '[ERROR]', | |
| '✅': '[SUCCESS]', | |
| '⚠️': '[WARNING]', | |
| '→': '->', | |
| '←': '<-', | |
| '…': '...', | |
| '–': '-', | |
| '—': '--', | |
| ''': "'", | |
| ''': "'", | |
| '"': '"', | |
| '"': '"', | |
| '•': '*', | |
| '©': '(c)', | |
| '®': '(R)', | |
| '™': '(TM)', | |
| '°': ' degrees', | |
| '±': '+/-', | |
| '×': 'x', | |
| '÷': '/', | |
| '≤': '<=', | |
| '≥': '>=' | |
| } | |
| for char, replacement in replacements.items(): | |
| content = content.replace(char, replacement) | |
| # Replace any remaining non-ASCII characters with their Unicode escape sequence | |
| def replace_non_ascii(match): | |
| char = match.group(0) | |
| return f"[U+{ord(char):04X}]" | |
| content = re.sub(r'[^\x00-\x7F]', replace_non_ascii, content) | |
| with open(output_path, 'w', encoding='utf-8') as f: | |
| f.write(content) | |
| print(f"Fixed file saved to {output_path}") | |
| return True | |
| except Exception as e: | |
| print(f"Error fixing {file_path}: {e}") | |
| return False | |
| if __name__ == "__main__": | |
| input_file = "app.py" | |
| output_file = "app_fixed.py" | |
| print(f"Checking {input_file} for Unicode characters...") | |
| find_unicode_chars(input_file) | |
| print(f"\nReplacing Unicode characters in {input_file}...") | |
| replace_unicode_chars(input_file, output_file) |