Method _migrate_from_csv

db_manager.py:450–533

Migrate data from legacy netkb.csv to SQLite database. Only runs if CSV exists and database is empty.

(self)

        # Clean up any duplicate entries (non-fatal if it fails)
        try:
            self.cleanup_duplicate_hosts()
        except Exception as e:
            logger.warning(f"Duplicate cleanup skipped: {e}")

        # Ensure legacy hostnames are cleaned up once on startup (non-fatal)
        try:
            self.sanitize_all_hostnames()
        except Exception as e:
            logger.warning(f"Hostname sanitization skipped: {e}")
    
    def _migrate_from_csv(self):
        """
        Migrate data from legacy netkb.csv to SQLite database.
        Only runs if CSV exists and database is empty.
        """
        if not os.path.exists(self.netkb_csv):
            logger.debug("No netkb.csv found - skipping migration")
            return

        # Check if database already has data
        with self.get_connection() as conn:
            cursor = conn.cursor()
            # Verify hosts table exists before querying
            cursor.execute("SELECT name FROM sqlite_master WHERE type='table' AND name='hosts'")
            if not cursor.fetchone():
                logger.warning("hosts table not found - skipping CSV migration")
                return

            cursor.execute("SELECT COUNT(*) FROM hosts")
            count = cursor.fetchone()[0]

            if count > 0:
                logger.debug(f"Database already contains {count} hosts - skipping CSV migration")
                return
        
        logger.info(f"Migrating data from {self.netkb_csv} to SQLite...")
        
        try:
            with open(self.netkb_csv, 'r', encoding='utf-8') as csvfile:
                reader = csv.DictReader(csvfile)
                migrated_count = 0
                
                for row in reader:
                    try:
                        mac = row.get('MAC', '').strip()
                        if not mac or mac.upper() == 'UNKNOWN':
                            continue
                        
                        # Convert CSV row to database format
                        host_data = {
                            'mac': mac,
                            'ip': row.get('IP', '').strip(),
                            'hostname': row.get('Hostname', '').strip(),
                            'vendor': row.get('Vendor', '').strip(),
                            'ports': row.get('Ports', '').strip(),
                            'services': row.get('Services', '').strip() or row.get('Service', '').strip(),
                            'vulnerabilities': row.get('Nmap Vulnerabilities', '').strip(),
                            'alive_count': self._safe_int(row.get('Alive Count', 0)),