iText PDF； 如何使用Java將jpeg2000轉換為jpg

Question

我正在嘗試使用java，iText和Java高級映像庫解決問題。 我的軟件系統使用ghostscript從PDF文件創建jpg縮略圖等。 然而，在CentOS 5.x上，ghostscript的最高版本是8.7，這是一個已知問題，即無法處理其中包含JPEG 2000圖像的PDF文件。 我的計划是先掃描文件，然后查看它是否包含jpeg2000圖像（我已經弄清楚了這部分）； 如果是這樣，則使用iText和Java Advanced Imaging庫（包含jpeg2000讀寫編解碼器）將包含的jpeg2000文件轉換為常規jpeg文件，然后將新的PDF文件傳遞給ghostscript。 下面的代碼嘗試執行此操作，但是會導致另一個包含jpeg2000文件的文件。 任何幫助，將不勝感激。

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

效果很好，但是GlassFish v3.1出現了一些問題。 Glassfish的行為就像在Classpath中沒有jai_imageio-1.1.jar一樣。 我修復了將jai_imageio.jar放入“ / path / to / glassfish / domains / domain1 / lib / ext /”文件夾中的問題。

Answer 2

我在Reece的PDFConverter中遇到了一些NullPointer問題，因為我的PDF 在CentOS 5.3的GhostScript中具有不同類型的嵌入元素-無法處理JPXDecode數據 。 因此，我進行了一些對象/類型檢查，並將輸出文件名添加到了命令行中。

其他一切都很棒，並且可以完美解決jpeg2000問題。 感謝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();
        }
    }

} 

Answer 3

因此，我設法自己解決了這一問題（在Bruno Lowagie的iText的幫助下-不錯的書）。 只是重申一下，我的目的是使用iText掃描PDF以查看它是否包含任何JPEG2000圖像，以及是否輸出相同的PDF，但內部JPEG2000圖像已替換為常規JPEG圖像。 這解決了致命的Ghostscript 8.7“無法處理JPXDecode數據”錯誤，但對於使PDF的iOS兼容也很有用。

因此，孩子們不再做； 開始...

步驟1）下載iText 5.x .jar文件，並下載jai_imageio-1.1.jar（Java高級映像庫，允許您轉換JPEG2000文件）

步驟2）創建一個名為PDFConverter.java的文件，並將以下代碼放入其中：

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();
        }
    }
} 

步驟3）以下列方式編譯上述文件：

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

步驟4）用PDF運行程序...

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

哎呀...