feat: extract text from fetched PDFs

server/tests/pdf-fixture.ts

@@ -0,0 +1,37 @@
+export function createPdf(pages: string[], encrypted = false): Uint8Array {
+  const fontId = 3 + pages.length * 2;
+  const objects = [
+    "<< /Type /Catalog /Pages 2 0 R >>",
+    `<< /Type /Pages /Kids [${pages.map((_, index) => `${3 + index * 2} 0 R`).join(" ")}] /Count ${pages.length} >>`,
+  ];
+  for (let index = 0; index < pages.length; index += 1) {
+    const pageId = 3 + index * 2;
+    const contentId = pageId + 1;
+    const text = pages[index]!;
+    const operators = Array.from({ length: Math.ceil(text.length / 100) }, (_, partIndex) => {
+      const part = text.slice(partIndex * 100, (partIndex + 1) * 100);
+      const escaped = part.replaceAll("\\", "\\\\").replaceAll("(", "\\(").replaceAll(")", "\\)");
+      return `(${escaped}) Tj`;
+    });
+    const content = text ? `BT /F1 12 Tf 72 720 Td ${operators.join(" ")} ET` : "";
+    objects.push(
+      `<< /Type /Page /Parent 2 0 R /MediaBox [0 0 612 792] /Resources << /Font << /F1 ${fontId} 0 R >> >> /Contents ${contentId} 0 R >>`,
+      `<< /Length ${Buffer.byteLength(content)} >>\nstream\n${content}\nendstream`,
+    );
+  }
+  objects.push("<< /Type /Font /Subtype /Type1 /BaseFont /Helvetica >>");
+  const encryptionId = objects.length + 1;
+  if (encrypted) objects.push(`<< /Filter /Standard /V 1 /R 2 /O <${"00".repeat(32)}> /U <${"00".repeat(32)}> /P -4 >>`);
+
+  let output = "%PDF-1.4\n";
+  const offsets = [0];
+  objects.forEach((object, index) => {
+    offsets.push(Buffer.byteLength(output));
+    output += `${index + 1} 0 obj\n${object}\nendobj\n`;
+  });
+  const xrefOffset = Buffer.byteLength(output);
+  output += `xref\n0 ${objects.length + 1}\n0000000000 65535 f \n`;
+  for (const offset of offsets.slice(1)) output += `${String(offset).padStart(10, "0")} 00000 n \n`;
+  output += `trailer\n<< /Size ${objects.length + 1} /Root 1 0 R${encrypted ? ` /Encrypt ${encryptionId} 0 R` : ""} >>\nstartxref\n${xrefOffset}\n%%EOF`;
+  return new TextEncoder().encode(output);
+}