Re: PDF to PDF/A conversion on java

[Tilman Hausherr]

On 19.12.2023 00:24, CowwoC wrote:
I'm going to need to do something like this in the near future. Are there
any good samples or documentation I can look at for this use-use?




import java.io.ByteArrayOutputStream;
import java.io.File;
import java.io.IOException;
import java.io.InputStream;
import javax.xml.transform.TransformerException;
import org.apache.pdfbox.Loader;
import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.pdmodel.PDDocumentInformation;
import org.apache.pdfbox.pdmodel.common.PDMetadata;
import org.apache.pdfbox.pdmodel.graphics.color.PDOutputIntent;
import org.apache.xmpbox.XMPMetadata;
import org.apache.xmpbox.schema.DublinCoreSchema;
import org.apache.xmpbox.schema.PDFAIdentificationSchema;
import org.apache.xmpbox.schema.XMPBasicSchema;
import org.apache.xmpbox.type.BadFieldValueException;
import org.apache.xmpbox.xml.XmpSerializer;


public final class ConvertToPDFA
{

    private ConvertToPDFA()
    {
    }

    public static void main(String[] args) throws IOException, 
TransformerException
    {
        String file = "XXXX\\testme1.pdf";
        String file2 = "XXXX\\testme1-pdfa.pdf";

        try (PDDocument doc = Loader.loadPDF(new File(file)))
        {
            doc.setVersion(1.4f);
            // add XMP metadata
            XMPMetadata xmp = XMPMetadata.createXMPMetadata();

            try
            {
                DublinCoreSchema dc = xmp.createAndAddDublinCoreSchema();
                dc.setTitle(file);

                PDFAIdentificationSchema id = 
xmp.createAndAddPDFAIdentificationSchema();
                id.setPart(1);
                id.setConformance("B");

                PDDocumentInformation info = new PDDocumentInformation();
                info.setCreator("PDFBox");
                XMPBasicSchema basicSchema = 
xmp.createAndAddXMPBasicSchema();
                basicSchema.setCreatorTool("PDFBox");

                XmpSerializer serializer = new XmpSerializer();
                ByteArrayOutputStream baos = new ByteArrayOutputStream();
                serializer.serialize(xmp, baos, true);

                PDMetadata metadata = new PDMetadata(doc);
                metadata.importXMPMetadata(baos.toByteArray());
                doc.getDocumentCatalog().setMetadata(metadata);
                doc.setDocumentInformation(info);
            }
            catch (BadFieldValueException e)
            {
                // won't happen here, as the provided value is valid
                throw new IllegalArgumentException(e);
            }

            // sRGB output intent
            InputStream colorProfile = 
ConvertToPDFA.class.getResourceAsStream(
                    "/org/apache/pdfbox/resources/pdfa/sRGB.icc");
            PDOutputIntent intent = new PDOutputIntent(doc, colorProfile);
            intent.setInfo("sRGB IEC61966-2.1");
            intent.setOutputCondition("sRGB IEC61966-2.1");
            intent.setOutputConditionIdentifier("sRGB IEC61966-2.1");
            intent.setRegistryName("http://www.color.org";);
            doc.getDocumentCatalog().addOutputIntent(intent);

            doc.save(file2);
        }
    }
}