Java PDPage.getAnnotations方法代码示例

import org.apache.pdfbox.pdmodel.PDPage; //导入方法依赖的package包/类
/**
 * <a href="https://stackoverflow.com/questions/45812696/pdfbox-delete-comment-maintain-strikethrough">
 * PDFBox delete comment maintain strikethrough
 * </a>
 * <br/>
 * <a href="https://expirebox.com/files/3d955e6df4ca5874c38dbf92fc43b5af.pdf">
 * only_fields.pdf
 * </a>
 * <a href="https://file.io/DTvqhC">
 * (alternative download)
 * </a>
 * <p>
 * The OP only wanted the comment removed, not the strike-through. Thus, we must
 * not remove the annotation but merely the comment building attributes.
 * </p>
 */
@Test
public void testRemoveLikeStephanImproved() throws IOException {
    final COSName POPUP = COSName.getPDFName("Popup");
    try (InputStream resource = getClass().getResourceAsStream("only_fields.pdf")) {
        PDDocument document = PDDocument.load(resource);
        List<PDAnnotation> annotations = new ArrayList<>();
        PDPageTree allPages = document.getDocumentCatalog().getPages();

        List<COSObjectable> objectsToRemove = new ArrayList<>();

        for (int i = 0; i < allPages.getCount(); i++) {
            PDPage page = allPages.get(i);
            annotations = page.getAnnotations();

            for (PDAnnotation annotation : annotations) {
                if ("StrikeOut".equals(annotation.getSubtype()))
                {
                    COSDictionary annotationDict = annotation.getCOSObject();
                    COSBase popup = annotationDict.getItem(POPUP);
                    annotationDict.removeItem(POPUP);
                    annotationDict.removeItem(COSName.CONTENTS); // plain text comment
                    annotationDict.removeItem(COSName.RC);       // rich text comment
                    annotationDict.removeItem(COSName.T);        // author

                    if (popup != null)
                        objectsToRemove.add(popup);
                }
            }

            annotations.removeAll(objectsToRemove);
        }

        document.save(new File(RESULT_FOLDER, "only_fields-removeImproved.pdf"));
    }
}
 

import org.apache.pdfbox.pdmodel.PDPage; //导入方法依赖的package包/类
public byte[] build() throws IOException {
    this.acroForm.setNeedAppearances(false);

    // Fix annotations
    for (PDPage page : this.pdfDocument.getPages()) {
        for (PDAnnotation annot : page.getAnnotations()) {
            annot.setPage(page);
        }
    }

    // Define font resources names used in PDF template
    final PDResources dr = new PDResources();
    dr.put(COSName.getPDFName("Helv"), PDType1Font.HELVETICA);
    dr.put(COSName.getPDFName("HeBo"), PDType1Font.HELVETICA_BOLD);
    this.acroForm.setDefaultResources(dr);

    // Convert form fields to text
    this.acroForm.flatten();

    final ByteArrayOutputStream bos = new ByteArrayOutputStream();
    pdfDocument.save(bos);
    pdfDocument.close();
    return bos.toByteArray();
}
 

import org.apache.pdfbox.pdmodel.PDPage; //导入方法依赖的package包/类
public static void extractAttachments(String pdfPath, String extractPath) throws IOException {

  PDDocument document = null;

  try {

    File input = new File(pdfPath);

    String filePath = input.getParent() + System.getProperty("file.separator");

    document = PDDocument.load(input);

    PDDocumentNameDictionary namesDictionary =
    new PDDocumentNameDictionary( document.getDocumentCatalog() );
    PDEmbeddedFilesNameTreeNode efTree = namesDictionary.getEmbeddedFiles();

    if (efTree != null) {

      Map<String, PDComplexFileSpecification> names = efTree.getNames();

      if (names != null) {
        extractFiles(names, filePath);
      } else {

        List<PDNameTreeNode<PDComplexFileSpecification>> kids = efTree.getKids();
        for (PDNameTreeNode<PDComplexFileSpecification> node : kids) {
          names = node.getNames();
          extractFiles(names, filePath);
        };

      };

    };

    for (PDPage page : document.getPages()) {
      for (PDAnnotation annotation : page.getAnnotations()) {
        if (annotation instanceof PDAnnotationFileAttachment) {
          PDAnnotationFileAttachment annotationFileAttachment = (PDAnnotationFileAttachment) annotation;
          PDComplexFileSpecification fileSpec = (PDComplexFileSpecification) annotationFileAttachment.getFile();
          PDEmbeddedFile embeddedFile = getEmbeddedFile(fileSpec);
          extractFile(filePath, fileSpec.getFilename(), embeddedFile);
        };
      };
    };

  } finally {

  };

}
 

import org.apache.pdfbox.pdmodel.PDPage; //导入方法依赖的package包/类
void removeWidgets(PDField targetField) throws IOException {
    if (targetField instanceof PDTerminalField) {
        List<PDAnnotationWidget> widgets = ((PDTerminalField)targetField).getWidgets();
        for (PDAnnotationWidget widget : widgets) {
            PDPage page = widget.getPage();
            if (page != null) {
                List<PDAnnotation> annotations = page.getAnnotations();
                boolean removed = false;
                for (PDAnnotation annotation : annotations) {
                    if (annotation.getCOSObject().equals(widget.getCOSObject()))
                    {
                        removed = annotations.remove(annotation);
                        break;
                    }
                }
                if (!removed)
                    System.out.println("Inconsistent annotation definition: Page annotations do not include the target widget.");
            } else {
                System.out.println("Widget annotation does not have an associated page; cannot remove widget.");
                // TODO: In this case iterate all pages and try to find and remove widget in all of them
            }
        }
    } else if (targetField instanceof PDNonTerminalField) {
        List<PDField> childFields = ((PDNonTerminalField)targetField).getChildren();
        for (PDField field : childFields)
            removeWidgets(field);
    } else {
        System.out.println("Target field is neither terminal nor non-terminal; cannot remove widgets.");
    }
}
 

import org.apache.pdfbox.pdmodel.PDPage; //导入方法依赖的package包/类
/**
 * <a href="https://stackoverflow.com/questions/45812696/pdfbox-delete-comment-maintain-strikethrough">
 * PDFBox delete comment maintain strikethrough
 * </a>
 * <br/>
 * <a href="https://expirebox.com/files/3d955e6df4ca5874c38dbf92fc43b5af.pdf">
 * only_fields.pdf
 * </a>
 * <a href="https://file.io/DTvqhC">
 * (alternative download)
 * </a>
 * <p>
 * Due to a bug in the <code>COSArrayList</code> usage for page annotations,
 * the indirect reference to the annotation in question is not removed from
 * the actual page annotations array.
 * </p>
 */
@Test
public void testRemoveLikeStephan() throws IOException {
    try (InputStream resource = getClass().getResourceAsStream("only_fields.pdf")) {
        PDDocument document = PDDocument.load(resource);
        List<PDAnnotation> annotations = new ArrayList<>();
        PDPageTree allPages = document.getDocumentCatalog().getPages();

        for (int i = 0; i < allPages.getCount(); i++) {
            PDPage page = allPages.get(i);
            annotations = page.getAnnotations();

            List<PDAnnotation> annotationToRemove = new ArrayList<PDAnnotation>();

            if (annotations.size() < 1)
                continue;
            else {
                for (PDAnnotation annotation : annotations) {

                    if (annotation.getContents() != null
                            && annotation.getContents().equals("Sample Strikethrough")) {
                        annotationToRemove.add(annotation);
                    }
                }
                annotations.removeAll(annotationToRemove);
            }
        }

        document.save(new File(RESULT_FOLDER, "only_fields-removeLikeStephan.pdf"));
    }
}