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高级成像库解决问题。我的软件系统使用ghostscript从PDF文件创建jpg缩略图等。但是在CentOS 5.x上，ghostscript的最高版本是8.7，其中存在一个无法处理包含JPEG 2000图像的PDF文件的已知问题。我的计划是首先扫描文件，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，那么使用iText和Java高级成像库（包含jpeg2000读取和写入编解码器）将包含的jpeg2000文件转换为常规jpeg文件＆amp;然后将新的PDF文件传递给ghostscript。下面的代码尝试这个，但导致另一个包含jpeg2000文件的文件。对此有任何帮助将非常感激。

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Bruno Lowagie的行动中得到了iText的一些帮助 - 很棒的书）。只是为了重新迭代，我的目的是使用iText扫描PDF以查看它是否包含任何JPEG2000图像，如果它输出相同的PDF但内部JPEG2000图像替换为常规JPEG图像。这解决了致命的鬼怪8.7＆＃39;无法处理JPXDecode数据＆＃39;错误，但也可以使PDF兼容iOS。

所以没有进一步做孩子;在这里...

步骤1）下载iText 5.x .jar文件，下载jai_imageio-1.1.jar（允许转换JPEG2000文件的Java高级成像库）

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）按以下方式编译上述文件：

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

步骤4）使用PDF ...

运行程序

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

Booyah ......

Answer 2

效果很好，但我在GlassFish v3.1上遇到了一些问题。 Glassfish的行为好像在Classpath中没有jai_imageio-1.1.jar。我修改了这个把jai_imageio.jar放在我的“/ path / to / glassfish / domains / domain1 / lib / ext /”文件夹中。

Answer 3

我在Reece的PDFConverter中遇到了一些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Object / Type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Reece：）

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();
        }
    }

}