Function useRemoteFileImport

frontend/src/hooks/useRemoteFileImport.ts:29–506

()

 * Custom hook for importing files from remote URLs
 */
export default function useRemoteFileImport() {
  const [isImporting, setIsImporting] = useState(false);
  const [importProgress, setImportProgress] = useState(0);
  const [importStatus, setImportStatus] = useState('');
  const [error, setError] = useState<string | null>(null);

  // DuckDB store access
  const duckDB = useDuckDBStore();
  
  // CSV parser
  const csvParser = useStreamingCSVParser();

  /**
   * Fetch a remote file with progress tracking
   */
  const fetchWithProgress = useCallback(async (
    url: string,
    options: {
      onProgress?: (bytesReceived: number, totalBytes?: number) => void;
      headers?: HeadersInit;
      timeout?: number;
    } = {}
  ): Promise<{ 
    stream: ReadableStream<Uint8Array>; 
    fileName: string;
    fileSize?: number;
    fileType?: string;
  }> => {
    const { onProgress, headers = {}, timeout = 30000 } = options;
    
    // Set up a timeout controller
    const controller = new AbortController();
    const timeoutId = setTimeout(() => controller.abort(), timeout);
    
    try {
      // Make initial HEAD request to get metadata
      const headResponse = await fetch(url, {
        method: 'HEAD',
        headers,
        signal: AbortSignal.timeout(5000) // Shorter timeout for HEAD
      }).catch(() => null); // Ignore HEAD failures, some servers don't support it
      
      // Get content length and filename from headers if available
      const contentLength = headResponse?.headers.get('content-length');
      const contentDisposition = headResponse?.headers.get('content-disposition');
      const contentType = headResponse?.headers.get('content-type');
      
      let fileName = '';
      
      // Try to get filename from content-disposition header
      if (contentDisposition) {
        const filenameMatch = /filename[^;=\n]*=((['"]).*?\2|[^;\n]*)/.exec(contentDisposition);
        if (filenameMatch && filenameMatch[1]) {
          fileName = filenameMatch[1].replace(/['"]/g, '').trim();
        }
      }
      
      // If no filename from header, extract from URL