Extract text from PDF

import * as pdfjsLib from "pdfjs-dist";
import workerUrl from "pdfjs-dist/build/pdf.worker.min.mjs?url";

pdfjsLib.GlobalWorkerOptions.workerSrc = workerUrl;

export async function extractPdfText(file: File): Promise<{ pages: string[]; text: string }> {
  const data = new Uint8Array(await file.arrayBuffer());
  const pdf = await pdfjsLib.getDocument({ data }).promise;
  const pages: string[] = [];

  for (let n = 1; n <= pdf.numPages; n += 1) {
    const page = await pdf.getPage(n);
    const content = await page.getTextContent();
    const pageText = content.items
      .map((item) => ("str" in item ? item.str : ""))
      .join(" ")
      .replace(/\s+/g, " ")
      .trim();
    pages.push(pageText);
  }

  await pdf.destroy();
  return { pages, text: pages.join("\n\n") };
}