I’m using the MuPDF.js library to extract annotations (specifically highlights) from a PDF document. While I can detect the annotations and their types, I’m struggling to retrieve the highlighted text. Here’s my current code:

import * as fs from "fs";
import * as mupdfjs from "mupdf/mupdfjs";

async function extractAnnotations() {
  try {
    // Read the PDF file as a buffer
    let fileData = fs.readFileSync("Example.pdf");

    // Open the document using mupdfjs.PDFDocument.openDocument
    let document = await mupdfjs.PDFDocument.openDocument(
      fileData,
      "application/pdf"
    );

    // Loop through all pages of the document
    let pageCount = document.countPages(); // Get total number of pages
    let i = 0;

    while (i < pageCount) {
      const page = new mupdfjs.PDFPage(document, i);
      const annots = page.getAnnotations();

      annots.forEach((annot, index) => {
        console.log(`Annotation ${index + 1}:`);
        console.log(`  Has Rect: ${annot.hasRect()}`);
        console.log(`  Contents: ${annot.getContents()}`);
        
      });

      i++;
    }
  } catch (err) {
    console.error("Error extracting annotations:", err);
  }
}

extractAnnotations();

Accessing Annotation Details:

annot.hasRect() returns false for highlight annotations.
annot.getContents() return nothing

Checked Documentation:

The MuPDF.js documentation doesn’t provide specific examples for extracting text associated with annotations like highlights.