gistfile1.java

package searchIndexer;

import java.io.File;

import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.util.PDFTextStripper;

public class PDFReader {
	
    //Extract text from PDF document 
	public DocStructure index(File file)
	{
		String content="";
		try
		{
			PDDocument doc = PDDocument.load(file);        
			try 
			{
				content= new PDFTextStripper().getText(doc);
			} 
			catch(Exception e) 
			{
				System.out.println("Unreadable file. Can not be indexed");
			}

	    	doc.close();
		}
		catch(Exception e)
		{
			e.printStackTrace();
		}
		
        return new DocStructure((long)file.getName().hashCode(), file.getName(), content);
	}
}