iText PDF；如何使用 Java 将 jpeg2000 转换为 jpg

Question

我正在尝试使用 java、iText 和 Java 高级成像库来解决问题。我的软件系统使用 ghostscript 从 PDF 文件创建 jpg 缩略图等。然而，在 CentOS 5.x 上，ghostscript 的最高版本是 8.7，它的一个已知问题是无法处理其中包含 JPEG 2000 图像的 PDF 文件。我的计划是先扫描文件，看看它是否包含 jpeg2000 图像（我已经弄清楚了这部分）；如果是这样，则使用 iText 和 Java Advanced Imaging 库（包含 jpeg2000 读写编解码器）将包含的 jpeg2000 文件转换为常规 jpeg 文件，然后将新的 PDF 文件传递​​给 ghostscript。下面的代码尝试这样做，但会生成另一个包含 jpeg2000 文件的文件。对此的任何帮助将不胜感激。

public class ImageReplacer{
    public static void main(String [] args){
        try{
            String RESULT = "";
            PdfReader reader = new PdfReader("pdf_containing_jpeg2000_images.pdf");
            PdfReaderContentParser parser = new PdfReaderContentParser(reader);
            MyImageRenderListener listener = new MyImageRenderListener(RESULT);
            MyImageConverterListener clistener = new MyImageConverterListener(RESULT);
            clistener.setReader(reader);
            for (int i = 1; i <= reader.getNumberOfPages(); i++) {
                parser.processContent(i, clistener);
            }   
            PdfStamper stamper = new PdfStamper(reader, new FileOutputStream("out.pdf"));
            stamper.close();            
        }catch(Exception e){
            e.printStackTrace();    
        }
    }
}
class MyImageConverterListener implements RenderListener {
    protected String path = "";
    protected PdfReader reader;
    public MyImageConverterListener(String path) {
        this.path = path;
    }
    public void beginTextBlock() { }
    public void endTextBlock() { }
    public void renderImage(ImageRenderInfo renderInfo) {
        try {
            PdfImageObject image = renderInfo.getImage();
            PdfName filter = (PdfName)image.get(PdfName.FILTER);
            if (PdfName.JPXDECODE.equals(filter)) {
                if(image.getDictionary().isStream()){
                    BufferedImage bi = image.getBufferedImage();
                    if (bi == null) return; 
                    int width = (int)bi.getWidth();
                    int height = (int)bi.getHeight();
                    ByteArrayOutputStream imgBytes = new ByteArrayOutputStream(); 
                    ImageIO.write(bi, "JPG", imgBytes);
                    PRStream stream = new PRStream(reader,imgBytes.toByteArray());
                    stream.clear();
                    stream.setData(imgBytes.toByteArray(), false, PRStream.NO_COMPRESSION);
                    stream.put(PdfName.TYPE, PdfName.XOBJECT);
                    stream.put(PdfName.SUBTYPE, PdfName.IMAGE);
                    stream.put(new PdfName("foo"+Math.random()), new PdfName("bar"+Math.random()));
                    stream.put(PdfName.FILTER, PdfName.DCTDECODE);
                    stream.put(PdfName.WIDTH, new PdfNumber(width));
                    stream.put(PdfName.HEIGHT, new PdfNumber(height));
                    stream.put(PdfName.BITSPERCOMPONENT, new PdfNumber(8));
                    stream.put(PdfName.COLORSPACE, PdfName.DEVICERGB);
                }
            }
        } catch (Exception e) {
            e.printStackTrace();
        }
    }
    public void renderText(TextRenderInfo renderInfo) { }
    public void setReader(PdfReader r){
        reader = r;
    }
}

Answer 1

所以我设法自己解决了这个问题（在 iText 的帮助下，Bruno Lowagie 的行动 - 很棒的书）。重申一下，我的意图是使用 iText 扫描 PDF 以查看它是否包含任何 JPEG2000 图像，以及它是否输出相同的 PDF，但内部 JPEG2000 图像替换为常规 JPEG 图像。这解决了致命的 ghostscript 8.7“无法处理 JPXDecode 数据”错误，但也有助于使 PDF 的 iOS 兼容。

所以孩子们不用再做任何事情了；来了……

步骤 1) 下载 iText 5.x .jar 文件，并下载 jai_imageio-1.1.jar（Java 高级成像库，可让您转换 JPEG2000 文件）

步骤 2) 创建一个名为 PDFConverter.java 的文件并将此代码放入其中：

import com.itextpdf.text.pdf.PdfReader;
import com.itextpdf.text.pdf.PdfName;
import com.itextpdf.text.pdf.PdfObject;
import com.itextpdf.text.pdf.PRStream;
import com.itextpdf.text.pdf.parser.PdfImageObject;
import com.itextpdf.text.pdf.PdfNumber;
import javax.imageio.ImageIO;
import java.awt.image.BufferedImage;
import com.itextpdf.text.pdf.PdfStamper;
import java.io.*;

public class PDFConverter{
    public static void main(String [] args){
        if(args.length==1){
            if(hasJpeg2000(args[0])){
                System.out.println("Contains JPEG2000 images: Converting them to JPEG..."); 
                convertPDF(args[0]);
                System.out.println("Done...");
            }else{
                System.out.println("Doesn't contain any JPEG2000 images: Nothing to be done...");   
            }
        }else{
            System.out.println("Please specify a PDF filename as a command line argument!");    
        }
    }
    public static boolean hasJpeg2000(String s){
        try{
            PdfReader reader = new PdfReader(s); 
            int n = reader.getXrefSize();
            PdfObject object; 
            PRStream stream; 
            for (int i = 0; i < n; i++) {
                object = reader.getPdfObject(i); 
                if (object == null || !object.isStream())continue; 
                stream = (PRStream)object; 
                PdfImageObject image = new PdfImageObject(stream);
                PdfName filter = (PdfName)image.get(PdfName.FILTER);
                if (PdfName.JPXDECODE.equals(filter)) {
                    return true;
                }
            }
        }catch(Exception e){
            e.printStackTrace();
        }
        return false;
    }
    public static void convertPDF(String s){
        try{
            PdfReader reader = new PdfReader(s); 
            int n = reader.getXrefSize();
            PdfObject object; 
            PRStream stream; 
            for (int i = 0; i < n; i++) {
                object = reader.getPdfObject(i); 
                if (object == null || !object.isStream())continue; 
                stream = (PRStream)object; 
                PdfImageObject image = new PdfImageObject(stream);
                PdfName filter = (PdfName)image.get(PdfName.FILTER);
                if (PdfName.JPXDECODE.equals(filter)) {
                    BufferedImage bi = image.getBufferedImage(); 
                    if (bi == null) continue; 
                    int width = (int)(bi.getWidth());
                    int height = (int)(bi.getHeight());
                    ByteArrayOutputStream imgBytes = new ByteArrayOutputStream(); 
                    ImageIO.write(bi, "JPG", imgBytes); 
                    stream.clear(); 
                    stream.setData(imgBytes.toByteArray(),false, PRStream.NO_COMPRESSION); 
                    stream.put(PdfName.TYPE, PdfName.XOBJECT); 
                    stream.put(PdfName.SUBTYPE, PdfName.IMAGE); 
                    stream.put(new PdfName("foo"+Math.random()), new PdfName("bar"+Math.random())); 
                    stream.put(PdfName.FILTER, PdfName.DCTDECODE); 
                    stream.put(PdfName.WIDTH, new PdfNumber(width)); 
                    stream.put(PdfName.HEIGHT, new PdfNumber(height)); 
                    stream.put(PdfName.BITSPERCOMPONENT,new PdfNumber(8)); 
                    stream.put(PdfName.COLORSPACE, PdfName.DEVICERGB);
                }
            }
            PdfStamper stamper = new PdfStamper(reader, new FileOutputStream("out.pdf")); stamper.close();
        }catch(Exception e){
            e.printStackTrace();
        }
    }
} 

步骤3）按如下方式编译上述文件：

javac -cp .:iText-5.0.4.jar:jai_imageio-1.1.jar PDFConverter.java

第 4 步）使用 PDF 运行程序...

java -cp .:iText-5.0.4.jar:jai_imageio-1.1.jar PDFConverter PDFFileName.pdf

嘘……

Answer 2

效果很好，但我在使用 GlassFish v3.1 时遇到了一些问题。 Glassfish 的行为就像 Classpath 中没有 jai_imageio-1.1.jar 一样。我修复了这个问题，将 jai_imageio.jar 放在我的“/path/to/glassfish/domains/domain1/lib/ext/”文件夹中。

Answer 3

我在使用 Reece 的 PDFConverter 时遇到了一些 NullPointer 问题，因为我的 PDF 在 GhostScript on CentOS 5.3 - Unable to process JPXDecode data 中有不同类型的嵌入元素。所以我做了一些对象/类型检查并将输出文件名添加到命令行。

其他一切都很棒，并且非常适合图像 jpeg2000 问题。感谢里斯 :)

import com.itextpdf.text.pdf.PdfReader;
import com.itextpdf.text.pdf.PdfName;
import com.itextpdf.text.pdf.PdfObject;
import com.itextpdf.text.pdf.*;
import com.itextpdf.text.pdf.PRStream;
import com.itextpdf.text.pdf.parser.PdfImageObject;
import com.itextpdf.text.pdf.PdfNumber;
import javax.imageio.ImageIO;
import java.awt.image.BufferedImage;
import com.itextpdf.text.pdf.PdfStamper;
import java.io.*;

public class PDFConverter{

    public static void main(String [] args){
        if(args.length==2){
            if(hasJpeg2000(args[0])){
                System.out.println("Contains JPEG2000 images: Converting them to JPEG..."); 
                convertPDF(args[0], args[1]);
                System.out.println("Done...");
            }else{
                System.out.println("Doesn't contain any JPEG2000 images: Nothing to be done...");
            }
        }else{
            System.out.println("Please specify a PDF filename and a output filename as a command line arguments!");
        }
    }

    public static boolean hasJpeg2000(String s){
        try{
            PdfReader reader = new PdfReader(s); 
            int n = reader.getXrefSize();
            PdfObject object; 
            PRStream stream; 
            for (int i = 0; i < n; i++) {
                object = reader.getPdfObject(i); 
                if (object == null || !object.isStream())continue; 
                stream = (PRStream)object; 
                PdfObject pdfsubtype = stream.get(PdfName.SUBTYPE);
                System.out.println(pdfsubtype);
                if (pdfsubtype != null && pdfsubtype.toString().equals(PdfName.IMAGE.toString())) {
                    PdfImageObject image = new PdfImageObject(stream);
                    PdfName filter = (PdfName)image.get(PdfName.FILTER);
                    if (PdfName.JPXDECODE.equals(filter)) {
                        return true;
                    }
                }
            }
        }catch(Exception e){
            e.printStackTrace();
        }
        return false;
    }

    private static void filterObject(PdfImageObject image,PdfName filter,PRStream stream) throws java.io.IOException {
        if (PdfName.JPXDECODE.equals(filter)) {
            BufferedImage bi = image.getBufferedImage();
            if (bi == null) return;
            int width = (int)(bi.getWidth());
            int height = (int)(bi.getHeight());
            ByteArrayOutputStream imgBytes = new ByteArrayOutputStream();
            ImageIO.write(bi, "JPG", imgBytes);
            stream.clear();
            stream.setData(imgBytes.toByteArray(),false, PRStream.NO_COMPRESSION);
            stream.put(PdfName.TYPE, PdfName.XOBJECT);
            stream.put(PdfName.SUBTYPE, PdfName.IMAGE);
            stream.put(new PdfName("foo"+Math.random()), new PdfName("bar"+Math.random()));
            stream.put(PdfName.FILTER, PdfName.DCTDECODE);
            stream.put(PdfName.WIDTH, new PdfNumber(width));
            stream.put(PdfName.HEIGHT, new PdfNumber(height));
            stream.put(PdfName.BITSPERCOMPONENT,new PdfNumber(8));
            stream.put(PdfName.COLORSPACE, PdfName.DEVICERGB);
        }
    }

    public static void convertPDF(String s, String out){
        try{
            PdfReader reader = new PdfReader(s); 
            int n = reader.getXrefSize();
            PdfObject object; 
            PRStream stream; 
            for (int i = 0; i < n; i++) {
                object = reader.getPdfObject(i); 
                if (object == null || !object.isStream())continue; 
                stream = (PRStream)object; 
                PdfObject pdfsubtype = stream.get(PdfName.SUBTYPE);
                if (pdfsubtype != null && pdfsubtype.toString().equals(PdfName.IMAGE.toString())) {
                    PdfImageObject image = new PdfImageObject(stream);
                    Object listOrName = image.get(PdfName.FILTER);
                    if (listOrName instanceof PdfName) {
                        PdfName filter = (PdfName)image.get(PdfName.FILTER);
                        filterObject(image, filter, stream);
                    }
                    else if (listOrName instanceof PdfArray) {
                        PdfArray list = (PdfArray)image.get(PdfName.FILTER);
                        for (int j = 0; j < list.size(); j++) {
                            PdfName filter = list.getAsName(j);
                            filterObject(image, filter, stream);
                        }
                    }
                    else {
                        System.err.println("Unknown Obejcttype: " + listOrName);
                    }
                }
            }
            PdfStamper stamper = new PdfStamper(reader, new FileOutputStream(out)); stamper.close();
        } catch(Exception e){
            e.printStackTrace();
        }
    }

}