// PDF text extraction using pdfjs-dist legacy build (Node.js compatible, no canvas/DOMMatrix)

// Force Next.js file tracer to include the worker file in standalone builds
import 'pdfjs-dist/legacy/build/pdf.worker.mjs';

/**
 * Extract all text from a PDF buffer.
 * Uses pdfjs-dist legacy build which works in Node.js without canvas or DOM APIs.
 */
export async function extractTextFromPdf(buffer: Buffer): Promise<string> {
  const pdfjsLib = await import('pdfjs-dist/legacy/build/pdf.mjs');

  // Resolve the worker path at runtime so pdfjs can find it in standalone builds
  const { createRequire } = await import('module');
  const require = createRequire(import.meta.url ?? __filename);
  pdfjsLib.GlobalWorkerOptions.workerSrc = require.resolve(
    'pdfjs-dist/legacy/build/pdf.worker.mjs',
  );

  const data = new Uint8Array(buffer);
  const doc = await pdfjsLib.getDocument({
    data,
    useSystemFonts: true,
    isEvalSupported: false,
  }).promise;

  const pages: string[] = [];
  for (let i = 1; i <= doc.numPages; i++) {
    const page = await doc.getPage(i);
    const content = await page.getTextContent();
    const pageText = content.items
      .filter((item) => 'str' in item)
      .map((item) => (item as { str: string }).str)
      .join(' ');
    pages.push(pageText);
  }

  doc.destroy();
  return pages.join('\n');
}