Function extractFormSchema

examples/pdf-server/server.ts:1138–1225

(
  pdfDoc: PDFDocumentProxy,
  fieldObjects: Record<string, PdfJsFieldObject[]> | null,
)

}

export async function extractFormSchema(
  pdfDoc: PDFDocumentProxy,
  fieldObjects: Record<string, PdfJsFieldObject[]> | null,
): Promise<{
  type: "object";
  properties: Record<string, PrimitiveSchemaDefinition>;
  required?: string[];
} | null> {
  if (!fieldObjects || Object.keys(fieldObjects).length === 0) {
    return null;
  }

  const properties: Record<string, PrimitiveSchemaDefinition> = {};
  for (const [name, fields] of Object.entries(fieldObjects)) {
    // pdfjs returns the full field-tree array: for separated structures
    // (pdf-lib) the typed widget is at [1+] behind a container at [0]; for
    // merged/leaf entries (W-9, most authoring tools) it's at [0]. Pick the
    // first entry that actually has a field type.
    const field = fields.find((f) => f.type) ?? fields[0];
    if (!field.editable) continue;

    switch (field.type) {
      case "text":
        properties[name] = { type: "string", title: name };
        break;
      case "checkbox":
        properties[name] = { type: "boolean", title: name };
        break;
      case "radiobutton": {
        const options = fields
          .map((f) => f.exportValues)
          .filter((v): v is string => !!v && v !== "Off");
        properties[name] =
          options.length > 0
            ? { type: "string", title: name, enum: options }
            : { type: "string", title: name };
        break;
      }
      case "combobox":
      case "listbox": {
        const items = field.items?.map((i) => i.exportValue).filter(Boolean);
        properties[name] =
          items && items.length > 0
            ? { type: "string", title: name, enum: items }
            : { type: "string", title: name };
        break;
      }
      // Skip "button" (push buttons) and unknown types
    }
  }

  // Collect alternativeText labels from per-page annotations
  // (getFieldObjects doesn't include them)
  const fieldLabels = new Map<string, string>();
  try {
    for (let i = 1; i <= pdfDoc.numPages; i++) {
      const page = await pdfDoc.getPage(i);
      const annotations = await page.getAnnotations();