Text extraction from PDF using PDFBox 2.0

Question

I'm trying to use PDFBox 2.0 for text extraction. I would like to get information on the font size of specific characters and the position rectangle of that character on the page. I've implemented this in PDFBox 1.6 using a PDFTextStripper:

    PDFParser parser = new PDFParser(is);
    try{
        parser.parse();
    }catch(IOException e){

    }
    COSDocument cosDoc = parser.getDocument();
    PDDocument pdd = new PDDocument(cosDoc);
    final StringBuffer extractedText = new StringBuffer();
    PDFTextStripper textStripper = new PDFTextStripper(){
        @Override
        protected void processTextPosition(TextPosition text) {
            extractedText.append(text.getCharacter());
            logger.debug("text position: "+text.toString());
        }
    };
    textStripper.setSuppressDuplicateOverlappingText(false);
    for(int pageNum = 0;pageNum<pdd.getNumberOfPages();pageNum++){
        PDPage page = (PDPage) pdd.getDocumentCatalog().getAllPages().get(pageNum);
        textStripper.processStream(page, page.findResources(), page.getContents().getStream());
    }
    pdd.close();

But in the 2.0 version of PDFBox, the processStream method has been removed. How can I achieve the same with PDFBox 2.0?

I've tried the following:

        PDDocument pdd = PDDocument.load(inputStream);
        PDFTextStripper textStripper = new PDFTextStripper(){
            @Override
            protected void processTextPosition(TextPosition text){
                int pos = PDFdocument.length();
                String textadded = text.getUnicode();
                Range range = new Range(pos,pos+textadded.length());
                int pagenr = this.getCurrentPageNo();
                Rectangle2D rect = new Rectangle2D.Float(text.getX(),text.getY(),text.getWidth(),text.getHeight());
            }
        };
        textStripper.setSuppressDuplicateOverlappingText(false);
        for(int pageNum = 0;pageNum<pdd.getNumberOfPages();pageNum++){
            PDPage page = (PDPage) pdd.getDocumentCatalog().getPages().get(pageNum);
            textStripper.processPage(page);
        }
        pdd.close();

The processTextPosition(TextPosition text) method does not get called. Any suggestions would be very welcome.

Answer 1

The DrawPrintTextLocations example, suggested by @tilmanhausherr, provided the solution to my problem.

The parser is started using the following code (the inputStream is the input stream from the URL of the PDF file):

    PDDocument pdd = null;
    try {
        pdd = PDDocument.load(inputStream);
        PDFParserTextStripper stripper = new PDFParserTextStripper(PDFdocument,pdd);
        stripper.setSortByPosition(true);
        for (int i=0;i<pdd.getNumberOfPages();i++){
            stripper.stripPage(i);
        }
    } catch (IOException e) {
        // throw error
    } finally {
        if (pdd!=null) {
            try {
                pdd.close();
            } catch (IOException e) {

            }
        }
    }

This code uses a custom subclass of PDFTextStripper:

class PDFParserTextStripper extends PDFTextStripper {

    public PDFParserTextStripper() throws IOException {
        super();
    }


    public void stripPage(int pageNr) throws IOException {
        this.setStartPage(pageNr+1);
        this.setEndPage(pageNr+1);
        Writer dummy = new OutputStreamWriter(new ByteArrayOutputStream());
        writeText(document,dummy); // This call starts the parsing process and calls writeString repeatedly.
    }



    @Override
    protected void writeString(String string,List<TextPosition> textPositions) throws IOException {
        for (TextPosition text : textPositions) {
            System.out.println("String[" + text.getXDirAdj()+","+text.getYDirAdj()+" fs="+text.getFontSizeInPt()+" xscale="+text.getXScale()+" height="+text.getHeightDir()+" space="+text.getWidthOfSpace()+" width="+text.getWidthDirAdj()+" ] "+text.getUnicode());
        }
    }

}

Answer 2

Here is an implementation which uses @tilmanhausherr suggestion(s):

import java.io.ByteArrayOutputStream;
import java.io.File;
import java.io.FileInputStream;
import java.io.IOException;
import java.io.InputStream;
import java.io.OutputStreamWriter;
import java.io.Writer;
import java.util.List;
import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.text.PDFTextStripper;
import org.apache.pdfbox.text.TextPosition;

class PDFParserTextStripper extends PDFTextStripper 
{
    public PDFParserTextStripper(PDDocument pdd) throws IOException 
    {  
        super();
        document = pdd;
    }

    public void stripPage(int pageNr) throws IOException 
    {
        this.setStartPage(pageNr+1);
        this.setEndPage(pageNr+1);
        Writer dummy = new OutputStreamWriter(new ByteArrayOutputStream());
        writeText(document,dummy); // This call starts the parsing process and calls writeString repeatedly.
    }

    @Override
    protected void writeString(String string,List<TextPosition> textPositions) throws IOException 
    {
        for (TextPosition text : textPositions) {
            System.out.println("String[" + text.getXDirAdj()+","+text.getYDirAdj()+" fs="+text.getFontSizeInPt()+" xscale="+text.getXScale()+" height="+text.getHeightDir()+" space="+text.getWidthOfSpace()+" width="+text.getWidthDirAdj()+" ] "+text.getUnicode());
        }
    }

    public static void extractText(InputStream inputStream)
    {
        PDDocument pdd = null;

        try 
        {
            pdd = PDDocument.load(inputStream);
            PDFParserTextStripper stripper = new PDFParserTextStripper(pdd);
            stripper.setSortByPosition(true);
            for (int i=0; i<pdd.getNumberOfPages(); i++)
            {
                stripper.stripPage(i);
            }
        } 
        catch (IOException e) 
        {
            // throw error
        } 
        finally 
        {
            if (pdd != null) 
            {
                try 
                {
                    pdd.close();
                } 
                catch (IOException e) 
                {

                }
            }
        }
    }

    public static void main(String[] args) throws IOException
    {
        File f = new File("C:\\PathToYourPDF\\pdfFile.pdf");
        FileInputStream fis = null;

        try 
        {
            fis = new FileInputStream(f);
            extractText(fis);
        } 
        catch(IOException e) 
        {
            e.printStackTrace();
        } 
        finally 
        {
            try 
            {
                if(fis != null)
                    fis.close();
            } 
            catch(IOException ex)
            {
                ex.printStackTrace();
            }
        }
    }
}