[PDFBOX-4319] Parsing 100000 page pdf is slow

• Type: Bug
• Status: Closed
• Priority: Major
• Resolution: Fixed
• Affects Version/s: 2.0.11, 3.0.0 PDFBox
• Fix Version/s: 2.0.12, 3.0.0 PDFBox
• Component/s: Documentation, Parsing
• Assignee: Tilman Hausherr
• Reporter: Simon Steiner
• Created: 20/Sep/18 09:17
• Updated: 05/Oct/18 04:53
• Resolved: 20/Sep/18 18:33

Description

Parsing 100000 page pdf is slow, how do i speed it up?

import org.apache.pdfbox.contentstream.operator.Operator;
import org.apache.pdfbox.cos.COSBase;
import org.apache.pdfbox.cos.COSName;
import org.apache.pdfbox.pdfparser.PDFStreamParser;
import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.pdmodel.PDPage;
import java.io.File;
import java.io.IOException;
import java.util.ArrayList;
import java.util.List;
public class CheckPDF {
    public static void main(String[] args) throws IOException {
        PDDocument doc = PDDocument.load(new File("out.pdf"));
        for (int i=0; i<doc.getNumberOfPages(); i++) {
            System.out.println(i);
            PDPage page = doc.getPage(i);
            PDFStreamParser parser = new PDFStreamParser(page.getContents());
            parser.parse();
            List<Object> it = parser.getTokens();
            List<COSBase> arguments = new ArrayList<COSBase>();
            for (Object o : it) {
                if (o instanceof Operator) {
                    Operator op = (Operator)o;
                    if (op.getName().equals("Do")) {
                        COSName name = (COSName) arguments.get(0);
                        if (page.getResources().getXObject(name) == null) {
                            throw new RuntimeException(name + " not found");
                        }
                    }
                    arguments.clear();
                } else {
                    arguments.add((COSBase)o);
                }
            }
        }
        doc.close();
    }
}