example_usage.py

#!/usr/bin/env python3
"""
Example usage of CSV Processor for GSSOC 25 Dashboard Update

This script demonstrates how to use the CSV processor in practice
for the database migration task.
"""

from csv_processor import CSVProcessor
import json


def process_gssoc25_projects():
    """
    Process GSSOC 25 projects from CSV file
    This is the main function that would be used in the database migration script
    """
    print("Processing GSSOC 25 Projects from CSV")
    print("=" * 50)
    
    # Initialize processor
    csv_file = "Master sheet - Mapping.csv"
    processor = CSVProcessor(csv_file)
    
    # Process CSV with URL validation but without accessibility check
    # (accessibility check can be slow and is optional)
    projects = processor.process_csv(
        validate_urls=True, 
        check_accessibility=False
    )
    
    # Get valid projects for database insertion
    valid_projects = processor.get_valid_projects()
    invalid_projects = processor.get_invalid_projects()
    
    print(f"✓ Successfully processed {len(projects)} projects")
    print(f"✓ Valid projects ready for database: {len(valid_projects)}")
    print(f"⚠ Projects with issues: {len(invalid_projects)}")
    print()
    
    # Export data in format ready for MongoDB insertion
    db_ready_data = processor.export_to_dict(include_invalid=False)
    
    # Show some statistics
    print("Project Statistics:")
    print("-" * 20)
    
    # Tech stack analysis
    tech_stacks = {}
    for project in valid_projects:
        if project.tech_stack:
            # Simple keyword extraction
            stack = project.tech_stack.lower()
            if 'react' in stack:
                tech_stacks['React'] = tech_stacks.get('React', 0) + 1
            if 'node' in stack or 'nodejs' in stack:
                tech_stacks['Node.js'] = tech_stacks.get('Node.js', 0) + 1
            if 'python' in stack:
                tech_stacks['Python'] = tech_stacks.get('Python', 0) + 1
            if 'java' in stack and 'javascript' not in stack:
                tech_stacks['Java'] = tech_stacks.get('Java', 0) + 1
    
    print("Popular Tech Stacks:")
    for tech, count in sorted(tech_stacks.items(), key=lambda x: x[1], reverse=True)[:5]:
        print(f"  {tech}: {count} projects")
    print()
    
    # Mentor statistics
    total_mentors = sum(len(project.mentors) for project in valid_projects)
    avg_mentors = total_mentors / len(valid_projects) if valid_projects else 0
    print(f"Total mentors: {total_mentors}")
    print(f"Average mentors per project: {avg_mentors:.1f}")
    print()
    
    return db_ready_data, invalid_projects


def show_sample_projects(db_data, count=3):
    """Show sample projects that will be inserted into database"""
    print(f"Sample Projects (first {count}):")
    print("-" * 30)
    
    for i, project in enumerate(db_data[:count]):
        print(f"{i+1}. {project['project_name']}")
        print(f"   GitHub: {project['github_url']}")
        print(f"   Admin: {project['admin_name']}")
        print(f"   Tech: {project['tech_stack'][:100]}{'...' if len(project['tech_stack']) > 100 else ''}")
        print(f"   Mentors: {len(project['mentors'])}")
        print()


def show_problematic_projects(invalid_projects, count=5):
    """Show projects that need manual review"""
    if not invalid_projects:
        print("✓ No problematic projects found!")
        return
    
    print(f"Projects Requiring Manual Review (first {count}):")
    print("-" * 45)
    
    for i, project in enumerate(invalid_projects[:count]):
        print(f"{i+1}. {project.project_name}")
        print(f"   URL: {project.github_url}")
        print(f"   Issues: {', '.join(project.validation_errors)}")
        print()


def save_results(db_data, invalid_projects):
    """Save processing results to files"""
    
    # Save valid projects for database insertion
    with open('gssoc25_projects_valid.json', 'w', encoding='utf-8') as f:
        json.dump(db_data, f, indent=2, ensure_ascii=False)
    
    # Save invalid projects for manual review
    invalid_data = []
    for project in invalid_projects:
        invalid_data.append({
            'project_name': project.project_name,
            'github_url': project.github_url,
            'admin_name': project.admin_name,
            'issues': project.validation_errors
        })
    
    with open('gssoc25_projects_invalid.json', 'w', encoding='utf-8') as f:
        json.dump(invalid_data, f, indent=2, ensure_ascii=False)
    
    print("Results saved:")
    print(f"✓ Valid projects: gssoc25_projects_valid.json ({len(db_data)} projects)")
    print(f"⚠ Invalid projects: gssoc25_projects_invalid.json ({len(invalid_projects)} projects)")


def main():
    """Main function"""
    try:
        # Process the CSV file
        db_data, invalid_projects = process_gssoc25_projects()
        
        # Show samples
        show_sample_projects(db_data)
        show_problematic_projects(invalid_projects)
        
        # Save results
        save_results(db_data, invalid_projects)
        
        print("\n" + "=" * 50)
        print("CSV Processing Complete!")
        print("Ready for database migration (Task 2)")
        
    except Exception as e:
        print(f"Error: {str(e)}")
        raise


if __name__ == "__main__":
    main()