This sample locates article threads and outputs their coordinates to the console

LocateArticleThreads.java

/*
 * Copyright Datalogics, Inc. 2015
 */

package pdfjt.cookbook.document;

import com.adobe.internal.io.ByteReader;
import com.adobe.internal.io.InputStreamByteReader;
import com.adobe.pdfjt.pdf.document.PDFCatalogThreads;
import com.adobe.pdfjt.pdf.document.PDFDocument;
import com.adobe.pdfjt.pdf.document.PDFOpenOptions;
import com.adobe.pdfjt.pdf.interactive.navigation.PDFBead;
import com.adobe.pdfjt.pdf.interactive.navigation.PDFBead_First;
import com.adobe.pdfjt.pdf.interactive.navigation.PDFThread;
import com.adobe.pdfjt.pdf.interactive.navigation.PDFThreadInfo;
import java.io.InputStream;
import java.net.URL;
import java.net.URLConnection;

/**
 * This sample locates article threads and outputs their coordinates to the
 * console.
 */
public class LocateArticleThreads {

    private static final String inputPDFURL = "http://dev.datalogics.com/cookbook/document/ArticleThreads.pdf";

    static public void main(String[] args) throws Exception {

        // First read in the PDF file
        URLConnection connection = new URL(inputPDFURL).openConnection();
        connection.setRequestProperty("User-Agent",
                "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.11 (KHTML, like Gecko) Chrome/23.0.1271.95 Safari/537.11");
        connection.connect();
        InputStream fis = connection.getInputStream();
        ByteReader byteReader = new InputStreamByteReader(fis);
        PDFDocument pdfDocument = PDFDocument.newInstance(byteReader, PDFOpenOptions.newInstance());
        // Get the list of threads
        PDFCatalogThreads threads = pdfDocument.requireCatalog().getThreads();
        // There's only one thread in the sample file so we can just get the
        // first one.
        PDFThread pdfThread = threads.get(0);
        // Get the thread metadata (information) and output the properties
        PDFThreadInfo pdfThreadInfo = pdfThread.getI();
        System.out.println("Subject: " + pdfThreadInfo.getSubject());
        System.out.println("Title: " + pdfThreadInfo.getTitle());
        // Get the firstbead onthe thread and output the properties
        PDFBead_First pdfBeadFirst = pdfThread.getF();
        System.out.println("Bead: Page " + pdfBeadFirst.getPage().getPageNumber());
        System.out.println("  llx: " + pdfBeadFirst.getRect().llx());
        System.out.println("  lly: " + pdfBeadFirst.getRect().lly());
        System.out.println("  width: " + pdfBeadFirst.getRect().width());
        System.out.println("  height: " + pdfBeadFirst.getRect().height());
        System.out.println("");
        // Get the next bead then iterate through all of them until we get to
        // the first one again. Just like in Acrobat, the last bead references
        // the first.
        PDFBead pdfBead = pdfBeadFirst.getNext();
        while (pdfBead.getCosObject().getObjNum() != pdfBeadFirst.getCosObject().getObjNum()) {
            System.out.println("Bead: Page " + pdfBead.getPage().getPageNumber());
            System.out.println("  llx: " + pdfBead.getRect().llx());
            System.out.println("  lly: " + pdfBead.getRect().lly());
            System.out.println("  width: " + pdfBead.getRect().width());
            System.out.println("  height: " + pdfBead.getRect().height());
            System.out.println("");
            pdfBead = pdfBead.getNext();
        }

        // Save the file.
        System.out.println("Done!");
    }
}