PDFBox

gistfile1.txt

    /***
     * Bypass the Tika wrapper for PDFs and go directly to PDFBox since
     * Apache Tika 0.8 has a bug when processing PDFs.  This should be fixed
     * when Apache Tika 0.9 is released.
     * @param file
     * @param fileType
     * @param writer
     * @throws IOException
     * @throws ConversionException
     */
    public static void convertPDFBox(InputStream is, Writer writer) throws IOException, ConversionException {
        Boolean force = true;

        // use PDFBox as the Tika wrapper has a bug for PDFs
        PDDocument document = null;
        try {
            document = PDDocument.load(is, force); // force extraction

            stripper.setForceParsing(force); // continue when errors are encountered
            stripper.setSortByPosition(false); // text may not be in visual order.
            stripper.setShouldSeparateByBeads(true); // beads are articles

            stripper.writeText(document, writer);
        }
        finally {
            try {
                if (document != null) {
                    document.close();
                }
            }
            catch (Exception e) {
                throw new ConversionException(e);
            }
        }
    }