setup.py

#!/usr/bin/env python3
"""
Startup Script for Iran Legal Dashboard
======================================
Ensures proper initialization and debugging
"""

import os
import sys
import sqlite3
import logging
from pathlib import Path

# Setup logging
logging.basicConfig(
    level=logging.INFO,
    format='%(asctime)s - %(levelname)s - %(message)s'
)
logger = logging.getLogger(__name__)

def check_environment():
    """Check if running environment is properly configured"""
    logger.info("🔍 Checking environment...")
    
    # Check current directory
    cwd = os.getcwd()
    logger.info(f"📁 Current working directory: {cwd}")
    
    # Check for required files
    required_files = ['app.py', 'requirements.txt']
    src_required_files = ['src/streamlit_app.py'] if os.path.exists('src') else []
    
    all_required = required_files + src_required_files
    
    missing_files = []
    for file in all_required:
        if not os.path.exists(file):
            missing_files.append(file)
    
    if missing_files:
        logger.error(f"❌ Missing required files: {missing_files}")
        return False
    
    logger.info("✅ All required files found")
    return True

def setup_database():
    """Setup database with proper permissions"""
    logger.info("🗄️ Setting up database...")
    
    # Try different database paths
    db_paths = [
        "/tmp/iran_legal.db",
        "./iran_legal.db",
        "data/iran_legal.db"
    ]
    
    for db_path in db_paths:
        try:
            # Ensure directory exists
            db_dir = os.path.dirname(db_path)
            if db_dir and not os.path.exists(db_dir):
                os.makedirs(db_dir, exist_ok=True)
            
            # Test database connection
            with sqlite3.connect(db_path, timeout=10) as conn:
                conn.execute("SELECT 1")
                logger.info(f"✅ Database accessible at: {db_path}")
                return db_path
                
        except Exception as e:
            logger.warning(f"⚠️ Cannot access {db_path}: {e}")
            continue
    
    logger.error("❌ No accessible database path found")
    return None

def check_permissions():
    """Check write permissions for critical directories"""
    logger.info("🔐 Checking permissions...")
    
    test_dirs = ["/tmp", ".", "./data", "./src"]
    
    results = {}
    for test_dir in test_dirs:
        if os.path.exists(test_dir):
            try:
                test_file = os.path.join(test_dir, "test_write.tmp")
                with open(test_file, 'w') as f:
                    f.write("test")
                os.remove(test_file)
                results[test_dir] = True
                logger.info(f"✅ {test_dir} - Writable")
            except Exception as e:
                results[test_dir] = False
                logger.warning(f"❌ {test_dir} - Not writable: {e}")
        else:
            results[test_dir] = None
            logger.info(f"ℹ️ {test_dir} - Does not exist")
    
    return results

def verify_imports():
    """Verify all required imports work"""
    logger.info("📦 Verifying imports...")
    
    required_modules = [
        'streamlit',
        'pandas', 
        'plotly',
        'requests',
        'bs4',
        'sqlite3',
        'json',
        'hashlib',
        'datetime'
    ]
    
    failed_imports = []
    
    for module in required_modules:
        try:
            __import__(module)
            logger.info(f"✅ {module} - OK")
        except ImportError as e:
            failed_imports.append(module)
            logger.error(f"❌ {module} - Failed: {e}")
    
    if failed_imports:
        logger.error(f"❌ Failed imports: {failed_imports}")
        logger.info("💡 Run: pip install -r requirements.txt")
        return False
    
    return True

def create_sample_data(db_path):
    """Create sample data for testing"""
    logger.info("📝 Creating sample data...")
    
    try:
        with sqlite3.connect(db_path) as conn:
            # Check if data already exists
            cursor = conn.execute("SELECT COUNT(*) FROM documents")
            doc_count = cursor.fetchone()[0]
            
            if doc_count > 0:
                logger.info(f"ℹ️ Database already has {doc_count} documents")
                return True
            
            # Create sample document
            conn.execute("""
                INSERT INTO documents (title, content, source, category, ai_score, keywords, file_size, language)
                VALUES (?, ?, ?, ?, ?, ?, ?, ?)
            """, (
                "نمونه سند حقوقی",
                "این یک نمونه سند حقوقی برای تست سیستم است که شامل محتوای آزمایشی می‌باشد.",
                "سیستم تست",
                "قانون",
                0.75,
                '["نمونه", "حقوق", "تست"]',
                150,
                "fa"
            ))
            
            # Create sample scraped item
            conn.execute("""
                INSERT INTO scraped_items (id, url, title, content, domain, rating_score, word_count, status)
                VALUES (?, ?, ?, ?, ?, ?, ?, ?)
            """, (
                "sample_001",
                "https://dastour.ir/sample",
                "نمونه محتوای حقوقی",
                "این یک نمونه محتوای حقوقی جمع‌آوری شده از وب است.",
                "dastour.ir",
                0.80,
                25,
                "completed"
            ))
            
            conn.commit()
            logger.info("✅ Sample data created successfully")
            return True
            
    except Exception as e:
        logger.error(f"❌ Failed to create sample data: {e}")
        return False

def main():
    """Main startup function"""
    logger.info("🚀 Starting Iran Legal Dashboard initialization...")
    
    # Check environment
    if not check_environment():
        logger.error("❌ Environment check failed")
        return False
    
    # Check permissions
    check_permissions()
    
    # Verify imports
    if not verify_imports():
        logger.error("❌ Import verification failed")
        return False
    
    # Setup database
    db_path = setup_database()
    if not db_path:
        logger.error("❌ Database setup failed")
        return False
    
    # Create sample data
    create_sample_data(db_path)
    
    logger.info("✅ Initialization completed successfully!")
    logger.info("🎉 Ready to run: streamlit run app.py")
    
    return True

if __name__ == "__main__":
    success = main()
    if not success:
        sys.exit(1)