Merge pull request #754 from Stirling-Tools/fix_extract_image

fix: infinite recursion in `ImageFinder`

src/main/java/stirling/software/SPDF/controller/api/misc/AutoSplitPdfController.java

@@ -68,7 +68,9 @@ public class AutoSplitPdfController {
                 splitDocuments.add(new PDDocument());
             }
 
-            if (!splitDocuments.isEmpty() && !QR_CONTENT.equals(result) && !QR_CONTENT_OLD.equals(result)) {
+            if (!splitDocuments.isEmpty()
+                    && !QR_CONTENT.equals(result)
+                    && !QR_CONTENT_OLD.equals(result)) {
                 splitDocuments.get(splitDocuments.size() - 1).addPage(document.getPage(page));
             } else if (page == 0) {
                 PDDocument firstDocument = new PDDocument();

src/main/java/stirling/software/SPDF/controller/api/pipeline/ApiDocService.java

@@ -63,10 +63,7 @@ public class ApiDocService {
             outputToFileTypes.put("PPT", Arrays.asList("ppt", "pptx", "odp"));
             outputToFileTypes.put("XML", Arrays.asList("xml", "xsd", "xsl"));
             outputToFileTypes.put(
-                    "BOOK",
+                    "BOOK", Arrays.asList("epub", "mobi", "azw3", "fb2", "txt", "docx"));
-                    Arrays.asList(
-                            "epub", "mobi", "azw3", "fb2", "txt",
-                            "docx"));
             // type.
         }
 

src/main/java/stirling/software/SPDF/pdf/ImageFinder.java

@@ -1,131 +0,0 @@
-package stirling.software.SPDF.pdf;
-
-import java.awt.geom.Point2D;
-import java.io.IOException;
-import java.util.List;
-
-import org.apache.pdfbox.contentstream.operator.Operator;
-import org.apache.pdfbox.contentstream.operator.OperatorName;
-import org.apache.pdfbox.cos.COSBase;
-import org.apache.pdfbox.cos.COSName;
-import org.apache.pdfbox.pdmodel.PDPage;
-import org.apache.pdfbox.pdmodel.graphics.PDXObject;
-import org.apache.pdfbox.pdmodel.graphics.form.PDFormXObject;
-import org.apache.pdfbox.pdmodel.graphics.image.PDImage;
-import org.apache.pdfbox.pdmodel.graphics.image.PDImageXObject;
-
-public class ImageFinder extends org.apache.pdfbox.contentstream.PDFGraphicsStreamEngine {
-    private boolean hasImages = false;
-
-    public ImageFinder(PDPage page) {
-        super(page);
-    }
-
-    public boolean hasImages() {
-        return hasImages;
-    }
-
-    @Override
-    protected void processOperator(Operator operator, List<COSBase> operands) throws IOException {
-        String operation = operator.getName();
-        if (operation.equals(OperatorName.DRAW_OBJECT)) {
-            COSBase base = operands.get(0);
-            if (base instanceof COSName) {
-                COSName objectName = (COSName) base;
-                PDXObject xobject = getResources().getXObject(objectName);
-                if (xobject instanceof PDImageXObject) {
-                    hasImages = true;
-                } else if (xobject instanceof PDFormXObject) {
-                    PDFormXObject form = (PDFormXObject) xobject;
-                    ImageFinder innerFinder = new ImageFinder(getPage());
-                    innerFinder.processPage(getPage());
-                    if (innerFinder.hasImages()) {
-                        hasImages = true;
-                    }
-                }
-            }
-        }
-        super.processOperator(operator, operands);
-    }
-
-    @Override
-    public void appendRectangle(Point2D p0, Point2D p1, Point2D p2, Point2D p3) throws IOException {
-        // TODO Auto-generated method stub
-
-    }
-
-    @Override
-    public void drawImage(PDImage pdImage) throws IOException {
-        // TODO Auto-generated method stub
-
-    }
-
-    @Override
-    public void clip(int windingRule) throws IOException {
-        // TODO Auto-generated method stub
-
-    }
-
-    @Override
-    public void moveTo(float x, float y) throws IOException {
-        // TODO Auto-generated method stub
-
-    }
-
-    @Override
-    public void lineTo(float x, float y) throws IOException {
-        // TODO Auto-generated method stub
-
-    }
-
-    @Override
-    public void curveTo(float x1, float y1, float x2, float y2, float x3, float y3)
-            throws IOException {
-        // TODO Auto-generated method stub
-
-    }
-
-    @Override
-    public Point2D getCurrentPoint() throws IOException {
-        // TODO Auto-generated method stub
-        return null;
-    }
-
-    @Override
-    public void closePath() throws IOException {
-        // TODO Auto-generated method stub
-
-    }
-
-    @Override
-    public void endPath() throws IOException {
-        // TODO Auto-generated method stub
-
-    }
-
-    @Override
-    public void strokePath() throws IOException {
-        // TODO Auto-generated method stub
-
-    }
-
-    @Override
-    public void fillPath(int windingRule) throws IOException {
-        // TODO Auto-generated method stub
-
-    }
-
-    @Override
-    public void fillAndStrokePath(int windingRule) throws IOException {
-        // TODO Auto-generated method stub
-
-    }
-
-    @Override
-    public void shadingFill(COSName shadingName) throws IOException {
-        // TODO Auto-generated method stub
-
-    }
-
-    // ... rest of the overridden methods
-}

src/main/java/stirling/software/SPDF/utils/PdfUtils.java

@@ -2,8 +2,10 @@ package stirling.software.SPDF.utils;
 
 import java.awt.Graphics;
 import java.awt.image.BufferedImage;
+import java.awt.image.RenderedImage;
 import java.io.ByteArrayOutputStream;
 import java.io.IOException;
+import java.util.ArrayList;
 import java.util.List;
 import java.util.zip.ZipEntry;
 import java.util.zip.ZipOutputStream;
@@ -16,11 +18,15 @@ import javax.imageio.ImageWriter;
 import javax.imageio.stream.ImageOutputStream;
 
 import org.apache.pdfbox.Loader;
+import org.apache.pdfbox.cos.COSName;
 import org.apache.pdfbox.pdmodel.PDDocument;
 import org.apache.pdfbox.pdmodel.PDPage;
 import org.apache.pdfbox.pdmodel.PDPageContentStream;
 import org.apache.pdfbox.pdmodel.PDPageContentStream.AppendMode;
+import org.apache.pdfbox.pdmodel.PDResources;
 import org.apache.pdfbox.pdmodel.common.PDRectangle;
+import org.apache.pdfbox.pdmodel.graphics.PDXObject;
+import org.apache.pdfbox.pdmodel.graphics.form.PDFormXObject;
 import org.apache.pdfbox.pdmodel.graphics.image.JPEGFactory;
 import org.apache.pdfbox.pdmodel.graphics.image.LosslessFactory;
 import org.apache.pdfbox.pdmodel.graphics.image.PDImageXObject;
@@ -31,8 +37,6 @@ import org.slf4j.Logger;
 import org.slf4j.LoggerFactory;
 import org.springframework.web.multipart.MultipartFile;
 
-import stirling.software.SPDF.pdf.ImageFinder;
-
 public class PdfUtils {
 
     private static final Logger logger = LoggerFactory.getLogger(PdfUtils.class);
@@ -62,6 +66,23 @@ public class PdfUtils {
         }
     }
 
+    public static List<RenderedImage> getAllImages(PDResources resources) throws IOException {
+        List<RenderedImage> images = new ArrayList<>();
+
+        for (COSName name : resources.getXObjectNames()) {
+            PDXObject object = resources.getXObject(name);
+
+            if (object instanceof PDImageXObject) {
+                images.add(((PDImageXObject) object).getImage());
+
+            } else if (object instanceof PDFormXObject) {
+                images.addAll(getAllImages(((PDFormXObject) object).getResources()));
+            }
+        }
+
+        return images;
+    }
+
     public static boolean hasImages(PDDocument document, String pagesToCheck) throws IOException {
         String[] pageOrderArr = pagesToCheck.split(",");
         List<Integer> pageList =
@@ -94,9 +115,7 @@ public class PdfUtils {
     }
 
     public static boolean hasImagesOnPage(PDPage page) throws IOException {
-        ImageFinder imageFinder = new ImageFinder(page);
+        return getAllImages(page.getResources()).size() > 0;
-        imageFinder.processPage(page);
-        return imageFinder.hasImages();
     }
 
     public static boolean hasTextOnPage(PDPage page, String phrase) throws IOException {