ElementReader

Sample Java, Kotlin code for using Apryse Android SDK to traverse the page display list using ElementReader.

Learn more about our full PDF Data Extraction SDK Capabilities.

To start your free trial, get started with Android SDK.

Java

//---------------------------------------------------------------------------------------
// Copyright (c) 2001-2019 by PDFTron Systems Inc. All Rights Reserved.
// Consult legal.txt regarding legal and license information.
//---------------------------------------------------------------------------------------

package com.pdftron.android.pdfnetsdksamples.samples;

import com.pdftron.android.pdfnetsdksamples.OutputListener;
import com.pdftron.android.pdfnetsdksamples.PDFNetSample;
import com.pdftron.android.pdfnetsdksamples.R;
import com.pdftron.android.pdfnetsdksamples.util.Utils;
import com.pdftron.common.PDFNetException;
import com.pdftron.pdf.Element;
import com.pdftron.pdf.ElementReader;
import com.pdftron.pdf.PDFDoc;
import com.pdftron.pdf.PageIterator;
import com.pdftron.pdf.PathData;

import java.util.ArrayList;

public class ElementReaderTest extends PDFNetSample {

	private static OutputListener mOutputListener;

	private static ArrayList<String> mFileList = new ArrayList<>();

    public ElementReaderTest() {
        setTitle(R.string.sample_elementreader_title);
        setDescription(R.string.sample_elementreader_description);
    }

	@Override
	public void run(OutputListener outputListener) {
		super.run(outputListener);
		mOutputListener = outputListener;
		mFileList.clear();
		printHeader(outputListener);

        mOutputListener.println("-------------------------------------------------");
        mOutputListener.println("Sample 1 - Extract text data from all pages in the document.");
        mOutputListener.println("Opening the input pdf...");

        try (PDFDoc doc = new PDFDoc(Utils.getAssetTempFile(INPUT_PATH + "newsletter.pdf").getAbsolutePath()))    // Extract text data from all pages in the document
        {
            doc.initSecurityHandler();

            int pgnum = doc.getPageCount();

            PageIterator itr;
            ElementReader page_reader = new ElementReader();

            for (itr = doc.getPageIterator(); itr.hasNext(); )        //  Read every page
            {
                page_reader.begin(itr.next());
                ProcessElements(page_reader);
                page_reader.end();
            }
            mOutputListener.println("Done.");
        } catch (Exception e) {
            mOutputListener.printError(e.getStackTrace());
        }

		for (String file : mFileList) {
			addToFileList(file);
		}
		printFooter(outputListener);
	}

    static void ProcessElements(ElementReader reader) throws PDFNetException {
        for (Element element = reader.next(); element != null; element = reader.next())    // Read page contents
        {
			switch (element.getType()) 
			{
				case Element.e_path:                 // Process path data...
				{
					PathData data = element.getPathData();
					byte[] operators = data.getOperators();
					double[] points = data.getPoints();
				}
				break;
				case Element.e_text:                // Process text strings...
				{
					String data = element.getTextString();
					mOutputListener.println(data); 
				}
				break;
				case Element.e_form:                // Process form XObjects
				{
					reader.formBegin();
					ProcessElements(reader);
					reader.end();
				}
				break;
			}
        }
    }

}

Kotlin

//---------------------------------------------------------------------------------------
// Copyright (c) 2001-2019 by PDFTron Systems Inc. All Rights Reserved.
// Consult legal.txt regarding legal and license information.
//---------------------------------------------------------------------------------------

package com.pdftron.android.pdfnetsdksamples.samples

import com.pdftron.android.pdfnetsdksamples.OutputListener
import com.pdftron.android.pdfnetsdksamples.PDFNetSample
import com.pdftron.android.pdfnetsdksamples.R
import com.pdftron.android.pdfnetsdksamples.util.Utils
import com.pdftron.common.PDFNetException
import com.pdftron.pdf.Element
import com.pdftron.pdf.ElementReader
import com.pdftron.pdf.PDFDoc
import com.pdftron.pdf.PageIterator
import java.util.*

class ElementReaderTest : PDFNetSample() {
    init {
        setTitle(R.string.sample_elementreader_title)
        setDescription(R.string.sample_elementreader_description)
    }

    override fun run(outputListener: OutputListener?) {
        super.run(outputListener)
        mOutputListener = outputListener
        mFileList.clear()
        printHeader(outputListener!!)

        mOutputListener!!.println("-------------------------------------------------")
        mOutputListener!!.println("Sample 1 - Extract text data from all pages in the document.")
        mOutputListener!!.println("Opening the input pdf...")
        // Extract text data from all pages in the document
        try {
            PDFDoc(Utils.getAssetTempFile(PDFNetSample.INPUT_PATH + "newsletter.pdf")!!.absolutePath).use { doc ->
                doc.initSecurityHandler()

                val pgnum = doc.pageCount

                val itr: PageIterator
                val page_reader = ElementReader()

                itr = doc.pageIterator
                while (itr.hasNext())
                //  Read every page
                {
                    page_reader.begin(itr.next())
                    ProcessElements(page_reader)
                    page_reader.end()
                }

                mOutputListener!!.println("Done.")
            }
        } catch (e: Exception) {
            mOutputListener!!.printError(e.stackTrace)
        }

        for (file in mFileList) {
            addToFileList(file)
        }
        printFooter(outputListener)
    }

    companion object {

        private var mOutputListener: OutputListener? = null

        private val mFileList = ArrayList<String>()

        @Throws(PDFNetException::class)
        internal fun ProcessElements(reader: ElementReader) {
            var element: Element? = reader.next()
            while (element != null)
            // Read page contents
            {
                when (element.type) {
                    Element.e_path                 // Process path data...
                    -> {
                        val data = element.pathData
                        val operators = data.operators
                        val points = data.points
                    }
                    Element.e_text                // Process text strings...
                    -> {
                        val data = element.textString
                        mOutputListener!!.println(data)
                    }
                    Element.e_form                // Process form XObjects
                    -> {
                        reader.formBegin()
                        ProcessElements(reader)
                        reader.end()
                    }
                }
                element = reader.next()
            }
        }
    }

}