setup.py

# setup.py - Run this first to fix the import issue in neurolex_v4_dataset.py
# Usage: python setup.py

"""
This script fixes the missing import in neurolex_v4_dataset.py.
Run once after cloning the repo:
    python setup.py
"""

def fix_dataset_import():
    """Add the missing CharTokenizer import to neurolex_v4_dataset.py"""
    
    filepath = 'neurolex_v4_dataset.py'
    
    with open(filepath, 'r') as f:
        content = f.read()
    
    # Check if fix is already applied
    if 'from neurolex_v4_model import CharTokenizer' in content:
        print("✅ Import already present - no fix needed")
        return
    
    # Add the import after 'import math'
    old = "import math\n"
    new = "import math\n\nfrom neurolex_v4_model import CharTokenizer\n"
    
    if old in content:
        content = content.replace(old, new, 1)  # Replace only first occurrence
        with open(filepath, 'w') as f:
            f.write(content)
        print("✅ Fixed: Added 'from neurolex_v4_model import CharTokenizer' to neurolex_v4_dataset.py")
    else:
        print("⚠️  Could not find insertion point. Please manually add:")
        print("    from neurolex_v4_model import CharTokenizer")
        print("  after the 'import math' line in neurolex_v4_dataset.py")


if __name__ == '__main__':
    fix_dataset_import()
    
    # Verify the fix works
    print("\nVerifying imports...")
    try:
        from neurolex_v4_model import CharTokenizer, NeuroLexV4, create_model
        from neurolex_v4_dataset import NeuroLexDataset, create_dataloaders
        print("✅ All imports successful!")
    except Exception as e:
        print(f"❌ Import error: {e}")