Function extractFormFieldInfo

examples/pdf-server/server.ts:1079–1136

* Extract detailed form field info (name, type, page, bounding box, label) * from a PDF. Bounding boxes are converted to model coordinates (top-left origin).

(
  pdfDoc: PDFDocumentProxy,
)

 * from a PDF. Bounding boxes are converted to model coordinates (top-left origin).
 */
async function extractFormFieldInfo(
  pdfDoc: PDFDocumentProxy,
): Promise<FormFieldInfo[]> {
  const fields: FormFieldInfo[] = [];
  for (let i = 1; i <= pdfDoc.numPages; i++) {
    const page = await pdfDoc.getPage(i);
    const pageHeight = page.getViewport({ scale: 1.0 }).height;
    const annotations = await page.getAnnotations();
    for (const ann of annotations) {
      // Only include form widgets (annotationType 20)
      if (ann.annotationType !== 20) continue;
      if (!ann.rect) continue;

      const fieldName = ann.fieldName || "";
      const fieldType = ann.fieldType || "unknown";

      // PDF rect is [x1, y1, x2, y2] in bottom-left origin
      const x1 = Math.min(ann.rect[0], ann.rect[2]);
      const y1 = Math.min(ann.rect[1], ann.rect[3]);
      const x2 = Math.max(ann.rect[0], ann.rect[2]);
      const y2 = Math.max(ann.rect[1], ann.rect[3]);
      const width = x2 - x1;
      const height = y2 - y1;

      // Convert to model coords (top-left origin): modelY = pageHeight - pdfY - height
      const modelY = pageHeight - y2;

      // Choice widgets (combo/listbox) carry `options` as
      // [{exportValue, displayValue}]. Expose export values — that's
      // what fill_form needs.
      let options: string[] | undefined;
      if (Array.isArray(ann.options) && ann.options.length > 0) {
        options = ann.options
          .map((o: { exportValue?: string }) => o?.exportValue)
          .filter((v: unknown): v is string => typeof v === "string");
      }

      fields.push({
        name: fieldName,
        type: fieldType,
        page: i,
        x: Math.round(x1),
        y: Math.round(modelY),
        width: Math.round(width),
        height: Math.round(height),
        ...(ann.alternativeText ? { label: ann.alternativeText } : undefined),
        // Radio: buttonValue is the per-widget export value — the only
        // thing distinguishing three `size [Btn]` lines from each other.
        ...(ann.radioButton && ann.buttonValue != null
          ? { exportValue: String(ann.buttonValue) }
          : undefined),
        ...(options?.length ? { options } : undefined),
      });
    }
  }

  return fields;
}