How to check that all used fonts are embedded in PDF with Java iText?

Question

How to check that all fonts that are used in a PDF file are embedded in the file with Java and iText? I have some existing PDF documents, and I'd like to validate that they use only embedded fonts.

This would require checking that no PDF standard fonts are used and other used fonts are embedded in the file.

Solution 1

Look at the ListUsedFonts example from iText in Action.

http://itextpdf.com/examples/iia.php?id=287

Looks like this will print out the fonts used in a pdf and if they are embedded.

/*
 * This class is part of the book "iText in Action - 2nd Edition"
 * written by Bruno Lowagie (ISBN: 9781935182610)
 * For more info, go to: http://itextpdf.com/examples/
 * This example only works with the AGPL version of iText.
 */

package part4.chapter16;

import java.io.FileOutputStream;
import java.io.IOException;
import java.io.PrintWriter;
import java.util.Set;
import java.util.TreeSet;

import part3.chapter11.FontTypes;

import com.itextpdf.text.DocumentException;
import com.itextpdf.text.pdf.PdfDictionary;
import com.itextpdf.text.pdf.PdfName;
import com.itextpdf.text.pdf.PdfReader;

public class ListUsedFonts {

    /** The resulting PDF file. */
    public static String RESULT
        = "results/part4/chapter16/fonts.txt";

    /**
     * Creates a Set containing information about the fonts in the src PDF file.
     * @param src the path to a PDF file
     * @throws IOException
     */
    public Set<String> listFonts(String src) throws IOException {
        Set<String> set = new TreeSet<String>();
        PdfReader reader = new PdfReader(src);
        PdfDictionary resources;
        for (int k = 1; k <= reader.getNumberOfPages(); ++k) {
            resources = reader.getPageN(k).getAsDict(PdfName.RESOURCES);
            processResource(set, resources);
        }
        reader.close();
        return set;
    }

    /**
     * Extracts the font names from page or XObject resources.
     * @param set the set with the font names
     * @param resources the resources dictionary
     */
    public static void processResource(Set<String> set, PdfDictionary resource) {
        if (resource == null)
            return;
        PdfDictionary xobjects = resource.getAsDict(PdfName.XOBJECT);
        if (xobjects != null) {
            for (PdfName key : xobjects.getKeys()) {
                processResource(set, xobjects.getAsDict(key));
            }
        }
        PdfDictionary fonts = resource.getAsDict(PdfName.FONT);
        if (fonts == null)
            return;
        PdfDictionary font;
        for (PdfName key : fonts.getKeys()) {
            font = fonts.getAsDict(key);
            String name = font.getAsName(PdfName.BASEFONT).toString();
            if (name.length() > 8 && name.charAt(7) == '+') {
                name = String.format("%s subset (%s)", name.substring(8), name.substring(1, 7));
            }
            else {
                name = name.substring(1);
                PdfDictionary desc = font.getAsDict(PdfName.FONTDESCRIPTOR);
                if (desc == null)
                    name += " nofontdescriptor";
                else if (desc.get(PdfName.FONTFILE) != null)
                    name += " (Type 1) embedded";
                else if (desc.get(PdfName.FONTFILE2) != null)
                    name += " (TrueType) embedded";
                else if (desc.get(PdfName.FONTFILE3) != null)
                    name += " (" + font.getAsName(PdfName.SUBTYPE).toString().substring(1) + ") embedded";
            }
            set.add(name);
        }
    }

    /**
     * Main method.
     *
     * @param    args    no arguments needed
     * @throws DocumentException 
     * @throws IOException
     */
    public static void main(String[] args) throws IOException, DocumentException {
        new FontTypes().createPdf(FontTypes.RESULT);
        Set<String> set = new ListUsedFonts().listFonts(FontTypes.RESULT);
        PrintWriter out = new PrintWriter(new FileOutputStream(RESULT));
        for (String fontname : set)
            out.println(fontname);
        out.flush();
        out.close();
    }
}

Solution 2

/**
 * Creates a set containing information about the not-embedded fonts within the src PDF file.
 * @param src the path to a PDF file
 * @throws IOException
 */
public Set<String> listFonts(String src) throws IOException {
    Set<String> set = new TreeSet<String>();
    PdfReader reader = new PdfReader(src);
    PdfDictionary resources;
    for (int k = 1; k <= reader.getNumberOfPages(); ++k) {
        resources = reader.getPageN(k).getAsDict(PdfName.RESOURCES);
        processResource(set, resources);
    }
    reader.close();
    return set;
}

/**
 * Finds out if the font is an embedded subset font
 * @param font name
 * @return true if the name denotes an embedded subset font
 */
private boolean isEmbeddedSubset(String name) {
    //name = String.format("%s subset (%s)", name.substring(8), name.substring(1, 7));
    return name != null && name.length() > 8 && name.charAt(7) == '+';
}

private void processFont(PdfDictionary font, Set<String> set) {
    String name = font.getAsName(PdfName.BASEFONT).toString();
    if(isEmbeddedSubset(name))
        return;

    PdfDictionary desc = font.getAsDict(PdfName.FONTDESCRIPTOR);

    //nofontdescriptor
    if (desc == null) {
        PdfArray descendant = font.getAsArray(PdfName.DESCENDANTFONTS);

        if (descendant == null) {
            set.add(name.substring(1));             
        }
        else {              
            for (int i = 0; i < descendant.size(); i++) {
                PdfDictionary dic = descendant.getAsDict(i);
                processFont(dic, set);                    
              }             
        }            
    }
    /**
     * (Type 1) embedded
     */
    else if (desc.get(PdfName.FONTFILE) != null)
        ;
    /**
     * (TrueType) embedded 
     */
    else if (desc.get(PdfName.FONTFILE2) != null)
        ;
    /**
     * " (" + font.getAsName(PdfName.SUBTYPE).toString().substring(1) + ") embedded" 
     */     
    else if (desc.get(PdfName.FONTFILE3) != null)
        ;
    else {
        set.add(name.substring(1));         
    }
}
/**
 * Extracts the names of the not-embedded fonts from page or XObject resources.
 * @param set the set with the font names
 * @param resources the resources dictionary
 */
public void processResource(Set<String> set, PdfDictionary resource) {
    if (resource == null)
        return;
    PdfDictionary xobjects = resource.getAsDict(PdfName.XOBJECT);
    if (xobjects != null) {
        for (PdfName key : xobjects.getKeys()) {
            processResource(set, xobjects.getAsDict(key));
        }
    }
    PdfDictionary fonts = resource.getAsDict(PdfName.FONT);
    if (fonts == null)
        return;
    PdfDictionary font;
    for (PdfName key : fonts.getKeys()) {
        font = fonts.getAsDict(key);                           
        processFont(font, set);
    }
}

The code above could be used to retrieve the fonts that are not embedded in the given PDF file. I've improved the code from iText in Action so that it can handle Font's DescendantFont node, too.