[PDFBOX-2775] ArrayIndexOutOfBoundsException in PDFTextStripper.processTextPosition()

• Type: Bug
• Status: Closed
• Priority: Major
• Resolution: Fixed
• Affects Version/s: 2.0.0
• Fix Version/s: 2.0.0
• Component/s: Text extraction
• Labels: beads
• External issue URL: http://www.oracle.com/technetwork/java/jaf-1-150219.pdf
• Assignee: Tilman Hausherr
• Reporter: Tilman Hausherr
• Created: 26/Apr/15 21:20
• Updated: 17/Mar/16 19:08
• Resolved: 21/Oct/15 21:13

Description

Reported by Andrew M. in the user mailing list:

Exception in thread "main" java.lang.ArrayIndexOutOfBoundsException: Array index out of range: 3
	at java.util.Vector.get(Vector.java:744)
	at org.apache.pdfbox.text.PDFTextStripper.processTextPosition(PDFTextStripper.java:903)
	at org.apache.pdfbox.text.PDFTextStripperByArea.processTextPosition(PDFTextStripperByArea.java:132)
	at org.apache.pdfbox.text.PDFTextStreamEngine.showGlyph(PDFTextStreamEngine.java:229)
	at org.apache.pdfbox.contentstream.PDFStreamEngine.showText(PDFStreamEngine.java:717)
	at org.apache.pdfbox.contentstream.PDFStreamEngine.showTextStrings(PDFStreamEngine.java:627)
	at org.apache.pdfbox.contentstream.operator.text.ShowTextAdjusted.process(ShowTextAdjusted.java:38)
	at org.apache.pdfbox.contentstream.PDFStreamEngine.processOperator(PDFStreamEngine.java:829)
	at org.apache.pdfbox.contentstream.PDFStreamEngine.processStreamOperators(PDFStreamEngine.java:490)
	at org.apache.pdfbox.contentstream.PDFStreamEngine.processStream(PDFStreamEngine.java:456)
	at org.apache.pdfbox.contentstream.PDFStreamEngine.processPage(PDFStreamEngine.java:167)
	at org.apache.pdfbox.text.PDFTextStreamEngine.processPage(PDFTextStreamEngine.java:117)
	at org.apache.pdfbox.text.PDFTextStripper.processPage(PDFTextStripper.java:347)
	at org.apache.pdfbox.text.PDFTextStripperByArea.extractRegions(PDFTextStripperByArea.java:113)
	at testpdfbox20.ExtractTextError.textFromBox(ExtractTextError.java:25)
	at testpdfbox20.ExtractTextError.main(ExtractTextError.java:45)

public class ExtractTextError
{
    static String textFromBox(PDDocument doc, int x, int y, int w, int h, int page)
            throws IOException
    {
        PDFTextStripperByArea stripper = new PDFTextStripperByArea();
        Rectangle rect = new Rectangle(x, y - h, w, h);
        stripper.addRegion("region", rect);
        int pageCount = doc.getDocumentCatalog().getPages().getCount();
        System.out.println("getting text from page #" + page + " of " + pageCount + " in doc.");
        if (page <= pageCount)
        {
            PDPage pp = doc.getDocumentCatalog().getPages().get(page - 1);
            stripper.extractRegions(pp);
            String text = stripper.getTextForRegion("region");
            System.out.println("text=" + text);
            return text;
        }
        else
        {
            return "No page #" + page;
        }
    }

    public static void main(String[] args) throws IOException
    {
        PDDocument doc = PDDocument.load(new File("jaf-1-150219.pdf"));
        textFromBox(doc, 33, 159, 216, 43, 1);
    }
}