org.apache.tika.parser.pdf.VisalloParserConfig Maven / Gradle / Ivy

Go to download

Show more of this group Show more artifacts with this name
Show all versions of visallo-gpw-tika-text-extractor Show documentation

There is a newer version: 4.0.0

Show newest version

package org.apache.tika.parser.pdf;

public class VisalloParserConfig extends PDFParserConfig {
    @Override
    public void configure(PDF2XHTML pdf2XHTML) {
        super.configure(pdf2XHTML);

        // Better paragraph detection
        pdf2XHTML.setDropThreshold(2.0f);
    }
}