renderImage函数pdfbox的字体问题

Question

I have an error when i read a page from a PDF document. this page contains a bar code which is done with a font (AAAAAC+Code3de9). this error appear only when i use the renderImage function.
I use the 2.0.17 version of pdfbox-app.

*déc. 02, 2019 9:34:13 AM org.apache.pdfbox.pdmodel.font.PDCIDFontType2 <init>
AVERTISSEMENT: Could not read embedded OTF for font AAAAAC+Code3de9
java.io.IOException: Illegal seek position: 2483278652
at org.apache.fontbox.ttf.MemoryTTFDataStream.seek(MemoryTTFDataStream.java:164)
at org.apache.fontbox.ttf.TrueTypeFont.readTable(TrueTypeFont.java:352)
at org.apache.fontbox.ttf.TTFParser.parseTables(TTFParser.java:173)
at org.apache.fontbox.ttf.TTFParser.parse(TTFParser.java:150)
at org.apache.fontbox.ttf.OTFParser.parse(OTFParser.java:79)
at org.apache.fontbox.ttf.OTFParser.parse(OTFParser.java:27)
at org.apache.fontbox.ttf.TTFParser.parse(TTFParser.java:106)
at org.apache.fontbox.ttf.OTFParser.parse(OTFParser.java:73)
at org.apache.pdfbox.pdmodel.font.PDCIDFontType2.<init>(PDCIDFontType2.java:112)
at org.apache.pdfbox.pdmodel.font.PDCIDFontType2.<init>(PDCIDFontType2.java:65)
at org.apache.pdfbox.pdmodel.font.PDFontFactory.createDescendantFont(PDFontFactory.java:139)
at org.apache.pdfbox.pdmodel.font.PDType0Font.<init>(PDType0Font.java:192)
at org.apache.pdfbox.pdmodel.font.PDFontFactory.createFont(PDFontFactory.java:97)
at org.apache.pdfbox.pdmodel.PDResources.getFont(PDResources.java:146)
at org.apache.pdfbox.contentstream.operator.text.SetFontAndSize.process(SetFontAndSize.java:61)
at org.apache.pdfbox.contentstream.PDFStreamEngine.processOperator(PDFStreamEngine.java:872)
at org.apache.pdfbox.contentstream.PDFStreamEngine.processStreamOperators(PDFStreamEngine.java:506)
at org.apache.pdfbox.contentstream.PDFStreamEngine.processStream(PDFStreamEngine.java:480)
at org.apache.pdfbox.contentstream.PDFStreamEngine.processPage(PDFStreamEngine.java:153)
at org.apache.pdfbox.rendering.PageDrawer.drawPage(PageDrawer.java:268)
at org.apache.pdfbox.rendering.PDFRenderer.renderImage(PDFRenderer.java:321)
at org.apache.pdfbox.rendering.PDFRenderer.renderImage(PDFRenderer.java:243)
at org.apache.pdfbox.rendering.PDFRenderer.renderImage(PDFRenderer.java:203)
at patrick.mart1.impose.ImposeKosmedias$1.run(ImposeKosmedias.java:370)
déc. 02, 2019 9:34:13 AM org.apache.pdfbox.pdmodel.font.PDCIDFontType2 findFontOrSubstitute
AVERTISSEMENT: Using fallback font LiberationSans for CID-keyed TrueType font AAAAAC+Code3de9*

Many thanks for your help

Answer 1

This is based on the RemoveAllText.java example from the source code download. It removes the selection of F2 in the content stream, and also removes the font in the resources. It makes the assumption that F2 is not really used, ie that there is no text related to F2. Compared to the official example, only "createTokensWithoutText" has been changed. I kept all the names even if the meaning is different, except for the class name.

So this code is really just for this file, or for files generated similarly.

public final class RemoveFontF2
{
    /**
     * Default constructor.
     */
    private RemoveFontF2()
    {
        // example class should not be instantiated
    }

    /**
     * This will remove all text from a PDF document.
     *
     * @param args The command line arguments.
     *
     * @throws IOException If there is an error parsing the document.
     */
    public static void main(String[] args) throws IOException
    {
        if (args.length != 2)
        {
            usage();
        }
        else
        {
            PDDocument document = PDDocument.load(new File(args[0]));
            if (document.isEncrypted())
            {
                System.err.println(
                        "Error: Encrypted documents are not supported for this example.");
                System.exit(1);
            }
            for (PDPage page : document.getPages())
            {
                List<Object> newTokens = createTokensWithoutText(page);
                PDStream newContents = new PDStream(document);
                writeTokensToStream(newContents, newTokens);
                page.setContents(newContents);
                processResources(page.getResources());
            }
            document.save(args[1]);
            document.close();
        }
    }

    private static void processResources(PDResources resources) throws IOException
    {
        for (COSName name : resources.getXObjectNames())
        {
            PDXObject xobject = resources.getXObject(name);
            if (xobject instanceof PDFormXObject)
            {
                PDFormXObject formXObject = (PDFormXObject) xobject;
                writeTokensToStream(formXObject.getContentStream(),
                        createTokensWithoutText(formXObject));
                processResources(formXObject.getResources());
            }
        }
        for (COSName name : resources.getPatternNames())
        {
            PDAbstractPattern pattern = resources.getPattern(name);
            if (pattern instanceof PDTilingPattern)
            {
                PDTilingPattern tilingPattern = (PDTilingPattern) pattern;
                writeTokensToStream(tilingPattern.getContentStream(),
                        createTokensWithoutText(tilingPattern));
                processResources(tilingPattern.getResources());
            }
        }
    }

    private static void writeTokensToStream(PDStream newContents, List<Object> newTokens) throws IOException
    {
        OutputStream out = newContents.createOutputStream(COSName.FLATE_DECODE);
        ContentStreamWriter writer = new ContentStreamWriter(out);
        writer.writeTokens(newTokens);
        out.close();
    }

    private static List<Object> createTokensWithoutText(PDContentStream contentStream) throws IOException
    {
        PDFStreamParser parser = new PDFStreamParser(contentStream);
        Object token = parser.parseNextToken();
        List<Object> newTokens = new ArrayList<Object>();
        while (token != null)
        {
            if (token instanceof Operator)
            {
                Operator op = (Operator) token;
                String opName = op.getName();
                if (OperatorName.SET_FONT_AND_SIZE.equals(opName) &&
                    newTokens.get(newTokens.size() - 2).equals(COSName.getPDFName("F2")))
                {
                    // remove the 2 arguments to this operator
                    newTokens.remove(newTokens.size() - 1);
                    newTokens.remove(newTokens.size() - 1);

                    token = parser.parseNextToken();
                    continue;
                }
            }
            newTokens.add(token);
            token = parser.parseNextToken();
        }
        // remove F2
        COSBase fontBase = contentStream.getResources().getCOSObject().getItem(COSName.FONT);
        if (fontBase instanceof COSDictionary)
        {
            ((COSDictionary) fontBase).removeItem(COSName.getPDFName("F2"));
        }
        return newTokens;
    }

    /**
     * This will print the usage for this document.
     */
    private static void usage()
    {
        System.err.println("Usage: java " + RemoveFontF2.class.getName() + " <input-pdf> <output-pdf>");
    }

}