使用PDFBox使某些字符在現有PDF文檔中不可見

Question

我嘗試使用Apache PDFBox從現有PDF中讀取“Tj”運算符。 當我完成這項任務時，我嘗試更換一些角色。 例如，讓我們考慮一個包含（hello world）Tj的pdf文檔，因此這段代碼將“hello”替換為“hi123”。 因此，修改后的文檔變為包含（hi123世界）Tj而不是（hello world）Tj。

我現在面臨的一個大問題是如何編輯此代碼以使“hello”成為文本呈現模式3（換句話說：文本呈現模式“不可見”）。 所以我不想用“hi123”替換“你好”，而是讓“你好”消失（模式不可見）。 因此，修改后的文檔只包含“世界”，其中“你好”變得不可見。

我的代碼到目前為止：

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

基本上你必須通過用八個標記3 Tr (hello) Tj 0 Tr ( world) Tj替換兩個標記(hello world) Tj來改變tokens列表。

因此，替換你的循環

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

通過類似的東西

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

最終代碼：

    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();  
    }
}