Pdf file to Xml Scenario

Question

Hi friends,
How can i do PDF file to XML scenario in XI.
Please help me in this
Thanks in advance
Sreedivia

Answer 1

Hi All,
We can convert PDF to XML using Java mapping. Below is the basic code for that:-
* To change the template for this generated file go to
* Window>Preferences>Java>Code Generation>Code and Comments
package Shubham1;
import java.io.FileInputStream;
import java.io.FileOutputStream;
import java.io.InputStream;
import java.io.OutputStream;
import java.util.HashMap;
import java.util.Map;
import com.lowagie.text.pdf.PdfReader;
import com.lowagie.text.pdf.parser.PdfTextExtractor;
import com.sap.aii.mapping.api.AbstractTrace;
import com.sap.aii.mapping.api.StreamTransformation;
* @author shubham.e.agarwal
* To change the template for this generated type comment go to
* Window>Preferences>Java>Code Generation>Code and Comments
public class Shubham2 implements StreamTransformation{
private Map map = null;
private AbstractTrace trace = null;
public void setParameter(Map arg0) {
  map = arg0; // Store reference to the mapping parameters
  if (map == null) {
   this.map = new HashMap();
/*public static void main(String[] args) { //FOR EXTERNAL STANDALONE TESTING
try {
  FileInputStream fin = new FileInputStream ("C:\\test.pdf"); //INPUT FILE (PAYLOAD)
  FileOutputStream fout = new FileOutputStream ("C:/Users/Shubham.e.agarwal/My Documents/pdfXML.xml"); //OUTPUT FILE (PAYLOAD)
  Shubham2 mapping = new Shubham2();
  mapping.execute(fin, fout);
  catch (Exception e1) {
  e1.printStackTrace();
public void execute(InputStream inputstream, OutputStream outputstream) {
  try {
   String msgType = "MT_shubham"; //A dummy Message type, please change it as per your requirement.
   String nameSpace = "http://Shubham"; //A dummy namespace, please change it as per your requirement.
   String str;
   str="<?xml version=\"1.0\" encoding=\"UTF-8\"?>\n"+ "<ns0:"+msgType+" "+"xmlns:ns0=\""+nameSpace+"\">";
   str = str + "\n<Record>";
   PdfReader reader = new PdfReader(inputstream);
   PdfTextExtractor pdf = new PdfTextExtractor(reader);
   str = str + pdf.getTextFromPage(1);
   str= str+"\n</Record>"+"\n</ns0:MT_shubham>";
   byte by[] = str.getBytes();
   outputstream.write(by);
   reader.close();
   outputstream.close();
   System.out.println(str);
  catch(Exception e){
   e.printStackTrace();