使用 PDFBox 使某些字符在现有 PDF 文档中不可见

Question

我尝试使用 Apache PDFBox. 从现有 PDF 中读取“Tj”运算符 当我完全完成这项任务时，我尝试替换一些字符。例如，让我们考虑一个包含 (hello world)Tj 的 pdf 文档，因此这段代码将“hello”替换为“hi123”。 因此修改后的文档变为包含 (hi123 world)Tj 而不是 (hello world)Tj。

我现在最大的问题是如何编辑此代码以使“hello”成为文本呈现模式 3（换句话说：文本呈现模式“不可见”）。所以我不想用“hi123”替换“hello”，而是让“hello”消失（模式不可见）。因此，修改后的文档只包含“世界”，而“hello”变得不可见。

到目前为止我的代码：

public class Test1 {
    private static Test1 tes; 
    private static final String src="...";
    private static PDPageContentStream content;
    private static PDType1Font font; 

    public static void CreatePdf(String src) throws IOException, COSVisitorException{
        PDRectangle rec= new PDRectangle(400,400);
        PDDocument document= null;
        document = new PDDocument();
        PDPage page = new PDPage(rec);
        document.addPage(page);
        PDDocumentInformation info=document.getDocumentInformation();
        info.setAuthor("PdfBox");
        info.setCreator("Pdf");
        info.setSubject("Stéganographie");
        info.setTitle("Stéganographie dans les documents PDF");
        info.setKeywords("Stéganographie, pdf");
        content= new PDPageContentStream(document, page);
        font= PDType1Font.HELVETICA;
        String texte="hello world";
        content.beginText();
        content.setFont(font, 12);
        content.moveTextPositionByAmount(15, 385);   
        // content.appendRawCommands("3 Tr");
        content.drawString(texte);
        content.endText();
        content.close();
        document.save("doc.pdf");
        document.close();       
    }

    public static void main(String[] args) throws IOException, COSVisitorException {
        tes= new Test1();
        tes.CreatePdf(src);
        PDDocument doc ;
        doc = PDDocument.load("doc.pdf");
        List pages = doc.getDocumentCatalog().getAllPages();  
        for (int i = 0; i < pages.size(); i++)  {
            PDPage page = (PDPage) pages.get(i);  
            PDStream contents = page.getContents();  
            PDFStreamParser parser = new PDFStreamParser(contents.getStream()); 
            parser.parse();  
            List tokens = parser.getTokens();  
            for (int j = 0; j < tokens.size(); j++)  
            {  
                Object next = tokens.get(j); 
                if (next instanceof PDFOperator)  {
                    PDFOperator op = (PDFOperator) next;  
                    // Tj and TJ are the two operators that display strings in a PDF  
                    if (op.getOperation().equals("Tj"))  
                    { 
                        // Tj takes one operator and that is the string  
                        // to display so lets update that operator 
                        COSString previous = (COSString) tokens.get(j - 1);  
                        String string = previous.getString();  
                        System.out.println(string);
                        //Word you want to change. Currently this code changes word "hello" to "hi123"
                        string = string.replaceFirst("hello", "hi123"); 
                        previous.reset();  
                        previous.append(string.getBytes("ISO-8859-1"));
                    }
                }      
            }
            // now that the tokens are updated we will replace the page content stream.
            PDStream updatedStream = new PDStream(doc);  
            OutputStream out = updatedStream.createOutputStream();  
            ContentStreamWriter tokenWriter = new ContentStreamWriter(out);  
            tokenWriter.writeTokens(tokens);  
            page.setContents(updatedStream);
        }
        doc.save("a.pdf"); 
        doc.close();  
    }
}

Answer 1

本质上，您必须通过将两个标记 (hello world) Tj 替换为八个标记 3 Tr (hello) Tj 0 Tr ( world) Tj 来更改 tokens 列表

因此，替换你的循环

List tokens = parser.getTokens();  
for (int j = 0; j < tokens.size(); j++)  
{
    [...]
}

类似

List tokens = parser.getTokens();  
for (int j = 0; j < tokens.size(); j++)  
{  
    Object next = tokens.get(j); 
    if (next instanceof PDFOperator)
    {
        PDFOperator op = (PDFOperator) next;  
        // Tj and TJ are the two operators that display strings in a PDF  
        if (op.getOperation().equals("Tj"))  
        { 
            tokens.set(j-1, COSInteger.get(3));
            tokens.set(j, PDFOperator.getOperator("Tr"));
            tokens.add(++j, new COSString("hello"));
            tokens.add(++j, PDFOperator.getOperator("Tj"));
            tokens.add(++j, COSInteger.get(0));
            tokens.add(++j, PDFOperator.getOperator("Tr"));
            tokens.add(++j, new COSString(" world"));
            tokens.add(++j, PDFOperator.getOperator("Tj"));
        }
    }      
}

Answer 2

最终代码：

    public class Test1 {
    private static Test1 tes; 
    private static final String src="...";
    private static PDPageContentStream content;
    private static PDType1Font font; 
    public static void CreatePdf(String src) throws IOException, COSVisitorException{
    PDRectangle rec= new PDRectangle(400,400);
    PDDocument document= null;
    document = new PDDocument();
    PDPage page = new PDPage(rec);
    document.addPage(page);
    PDDocumentInformation info=document.getDocumentInformation();
    info.setAuthor("PdfBox");
    info.setCreator("Pdf");
    info.setSubject("Stéganographie");
    info.setTitle("Stéganographie dans les documents PDF");
    info.setKeywords("Stéganographie, pdf");
    content= new PDPageContentStream(document, page);
    font= PDType1Font.HELVETICA;
    String texte="hello world";
    content.beginText();
    content.setFont(font, 12);
    content.moveTextPositionByAmount(15, 385);   
    // content.appendRawCommands("3 Tr");
    content.drawString(texte);
    content.endText();
    content.close();
    document.save("doc.pdf");
    document.close();       
    }

    /**
     * @param args the command line arguments
     */
    public static void main(String[] args) throws IOException, COSVisitorException {
        // TODO code application logic here   
           tes= new Test1();
           tes.CreatePdf(src);
           PDDocument doc ;
           doc = PDDocument.load("doc.pdf");
           List pages = doc.getDocumentCatalog().getAllPages();  
           for (int i = 0; i < pages.size(); i++)  {
              PDPage page = (PDPage) pages.get(i);  
              PDStream contents = page.getContents();  
              PDFStreamParser parser = new PDFStreamParser(contents.getStream()); 
              parser.parse();  
              List tokens = parser.getTokens();  
                for (int j = 0; j < tokens.size(); j++)  
            {  
                  Object next = tokens.get(j); 
                     if (next instanceof PDFOperator)  {
                       PDFOperator op = (PDFOperator) next;  
                    // Tj and TJ are the two operators that display strings in a PDF  
                             if (op.getOperation().equals("Tj"))  
                    { 
                        // Tj takes one operator and that is the string  
                        // to display so lets update that operator 
                               //COSString previous = (COSString) tokens.get(j - 1);  
                               //String string = previous.getString();  
                               //System.out.println(string);
                               //Word you want to change. Currently this code changes word "hello" to "hi123"
                              // string = string.replaceFirst("hello", "hi123"); 
                              // previous.reset();  
                              // previous.append(string.getBytes("ISO-8859-1"));                    
            tokens.set(j-1, COSInteger.get(3));
            tokens.set(j, PDFOperator.getOperator("Tr"));
            tokens.add(++j, new COSString("hello"));
            tokens.add(++j, PDFOperator.getOperator("Tj"));
            tokens.add(++j, COSInteger.get(0));
            tokens.add(++j, PDFOperator.getOperator("Tr"));
            tokens.add(++j, new COSString(" world"));
            tokens.add(++j, PDFOperator.getOperator("Tj"));






                    }
                 }      
            }
                // now that the tokens are updated we will replace the page content stream.
            PDStream updatedStream = new PDStream(doc);  
            OutputStream out = updatedStream.createOutputStream();  
            ContentStreamWriter tokenWriter = new ContentStreamWriter(out);  
            tokenWriter.writeTokens(tokens);  
            page.setContents(updatedStream);
    }
      doc.save("a.pdf"); 
      doc.close();  
    }
}