Java Code Examples for org.apache.pdfbox.pdmodel.interactive.form.PDAcroForm#getFieldTree()

/**
 * Retrieve all signature fields from the document.
 * 
 * @return a <code>List</code> of <code>PDSignatureField</code>s
 * @throws IOException if no document catalog can be found.
 */
public List<PDSignatureField> getSignatureFields() throws IOException
{
    List<PDSignatureField> fields = new ArrayList<PDSignatureField>();
    PDAcroForm acroForm = getDocumentCatalog().getAcroForm();
    if (acroForm != null)
    {
        for (PDField field : acroForm.getFieldTree())
        {
            if (field instanceof PDSignatureField)
            {
                fields.add((PDSignatureField)field);
            }
        }
    }
    return fields;
}
 

/**
 * <a href="https://stackoverflow.com/questions/22074449/how-to-know-if-a-field-is-on-a-particular-page">
 * how to know if a field is on a particular page?
 * </a>
 * <p>
 * This sample document does not contain the optional page entry in its annotations.
 * Thus, the fast method fails in contrast to the safe one.
 * </p>
 */
@Test
public void testAFieldTwice() throws IOException
{
    System.out.println("aFieldTwice.pdf\n=================");
    try (   InputStream resource = getClass().getResourceAsStream("aFieldTwice.pdf")    )
    {
        PDDocument document = Loader.loadPDF(resource);
        PDAcroForm acroForm = document.getDocumentCatalog().getAcroForm();
        if (acroForm != null)
        {
            for (PDField field : acroForm.getFieldTree())
            {
                System.out.println(field.getFullyQualifiedName());
                for (PDAnnotationWidget widget : field.getWidgets())
                {
                    System.out.print(widget.getAnnotationName() != null ? widget.getAnnotationName() : "(NN)");
                    System.out.printf(" - fast: %s", determineFast(document, widget));
                    System.out.printf(" - safe: %s\n", determineSafe(document, widget));
                }
            }
        }
    }
    System.out.println();
}
 

/**
 * <a href="https://stackoverflow.com/questions/22074449/how-to-know-if-a-field-is-on-a-particular-page">
 * how to know if a field is on a particular page?
 * </a>
 * <p>
 * This sample document contains the optional page entry in its annotations.
 * Thus, the fast method returns the same result as the safe one.
 * </p>
 */
@Test
public void testTestDuplicateField2() throws IOException
{
    System.out.println("test_duplicate_field2.pdf\n=================");
    try (   InputStream resource = getClass().getResourceAsStream("test_duplicate_field2.pdf")    )
    {
        PDDocument document = Loader.loadPDF(resource);
        PDAcroForm acroForm = document.getDocumentCatalog().getAcroForm();
        if (acroForm != null)
        {
            for (PDField field : acroForm.getFieldTree())
            {
                System.out.println(field.getFullyQualifiedName());
                for (PDAnnotationWidget widget : field.getWidgets())
                {
                    System.out.print(widget.getAnnotationName() != null ? widget.getAnnotationName() : "(NN)");
                    System.out.printf(" - fast: %s", determineFast(document, widget));
                    System.out.printf(" - safe: %s\n", determineSafe(document, widget));
                }
            }
        }
    }
    System.out.println();
}
 

/**
 * <a href="http://stackoverflow.com/questions/39574021/how-can-the-internal-labels-of-the-editable-fields-in-an-acroform-pdf-be-found">
 * How can the internal labels of the editable fields in an acroform .pdf be found and listed?
 * </a>
 * <p>
 * This method retrieves the form field names from the given {@link PDDocument}. 
 * </p>
 */
List<String> getFormFieldNames(PDDocument pdDocument)
{
    PDAcroForm pdAcroForm = pdDocument.getDocumentCatalog().getAcroForm();
    if (pdAcroForm == null)
        return Collections.emptyList();

    List<String> result = new ArrayList<>();
    for (PDField pdField : pdAcroForm.getFieldTree())
    {
        if (pdField instanceof PDTerminalField)
        {
            result.add(pdField.getFullyQualifiedName());
        }
    }
    return result;
}
 

/**
 * <a href="https://stackoverflow.com/questions/56938135/pdfbox-inconsistent-pdtextfield-autosize-behavior-after-setvalue">
 * PDFBox Inconsistent PDTextField Autosize Behavior after setValue
 * </a>
 * <br/>
 * <a href="http://www.filedropper.com/0postfontload">
 * 0.pdf
 * </a>
 * <p>
 * Indeed, some fields look weird after fill-in; for some fields
 * this is due to weird pre-existing appearance streams. These can
 * be fixed as in {@link #testFill0DropOldAppearance()}.
 * </p>
 * @see #testFill0DropOldAppearance()
 * @see #testFill0DropOldAppearanceNoCombNoMax()
 * @see #testFill0DropOldAppearanceNoCombNoMaxNoMultiLine()
 */
@Test
public void testFill0LikeXenyal() throws IOException {
    try (   InputStream originalStream = getClass().getResourceAsStream("0.pdf");
            InputStream fontStream = getClass().getResourceAsStream("Lato-Regular.ttf"))
    {
        PDDocument doc = Loader.loadPDF(originalStream);
        PDAcroForm acroForm = doc.getDocumentCatalog().getAcroForm();

        PDType0Font font = PDType0Font.load(doc, fontStream, false);
        String font_name = acroForm.getDefaultResources().add(font).getName();

        for (PDField field : acroForm.getFieldTree()) {
            if (field instanceof PDTextField) {
                PDTextField textField = (PDTextField) field;
                textField.setDefaultAppearance(String.format("/%s 0 Tf 0 g", font_name));
                textField.setValue("Test");
            }
        }
        

        doc.save(new File(RESULT_FOLDER, "0-filledLikeXenyal.pdf"));
        doc.close();
    }        
}
 

/**
 * <a href="https://stackoverflow.com/questions/56938135/pdfbox-inconsistent-pdtextfield-autosize-behavior-after-setvalue">
 * PDFBox Inconsistent PDTextField Autosize Behavior after setValue
 * </a>
 * <br/>
 * <a href="http://www.filedropper.com/0postfontload">
 * 0.pdf
 * </a>
 * <p>
 * Removing the old appearance streams before setting the new field
 * values removes the compression of the Resident Name and Care
 * Providers Address fields. In the latter case, though, the lower
 * part of the field value now is cut off.
 * </p>
 * <p>
 * For some fields only the first two letters are visible. This is
 * due to them being two character comb fields. These can changed
 * as in {@link #testFill0DropOldAppearanceNoCombNoMax()}.
 * </p>
 * @see #testFill0LikeXenyal()
 * @see #testFill0DropOldAppearanceNoCombNoMax()
 * @see #testFill0DropOldAppearanceNoCombNoMaxNoMultiLine()
 */
@Test
public void testFill0DropOldAppearance() throws IOException {
    try (   InputStream originalStream = getClass().getResourceAsStream("0.pdf");
            InputStream fontStream = getClass().getResourceAsStream("Lato-Regular.ttf"))
    {
        PDDocument doc = Loader.loadPDF(originalStream);
        PDAcroForm acroForm = doc.getDocumentCatalog().getAcroForm();

        PDType0Font font = PDType0Font.load(doc, fontStream, false);
        String font_name = acroForm.getDefaultResources().add(font).getName();

        for (PDField field : acroForm.getFieldTree()) {
            if (field instanceof PDTextField) {
                PDTextField textField = (PDTextField) field;
                textField.setDefaultAppearance(String.format("/%s 0 Tf 0 g", font_name));
                textField.getWidgets().forEach(w -> w.getAppearance().setNormalAppearance((PDAppearanceEntry)null));
                textField.setValue("Test");
            }
        }
        

        doc.save(new File(RESULT_FOLDER, "0-filledDropOldAppearance.pdf"));
        doc.close();
    }        
}
 

/**
 * <a href="https://stackoverflow.com/questions/56938135/pdfbox-inconsistent-pdtextfield-autosize-behavior-after-setvalue">
 * PDFBox Inconsistent PDTextField Autosize Behavior after setValue
 * </a>
 * <br/>
 * <a href="http://www.filedropper.com/0postfontload">
 * 0.pdf
 * </a>
 * <p>
 * Resetting the comb flags and removing maximum lengths fixes the
 * appearance of the fields in which only the first two letters were
 * visible.
 * </p>
 * <p>
 * The problem of the lower part of the field value being cut off in
 * the Care Providers Address fields is due to PDFBox in case of 
 * multi line text fields using a fixed font height and not fine
 * tuning the vertical position of the field contents. In the case
 * at hand this can be fixed as in {@link #testFill0DropOldAppearanceNoCombNoMaxNoMultiLine()}.
 * </p>
 * @see #testFill0LikeXenyal()
 * @see #testFill0DropOldAppearance()
 * @see #testFill0DropOldAppearanceNoCombNoMaxNoMultiLine()
 */
@Test
public void testFill0DropOldAppearanceNoCombNoMax() throws IOException {
    final int FLAG_COMB = 1 << 24;

    try (   InputStream originalStream = getClass().getResourceAsStream("0.pdf");
            InputStream fontStream = getClass().getResourceAsStream("Lato-Regular.ttf"))
    {
        PDDocument doc = Loader.loadPDF(originalStream);
        PDAcroForm acroForm = doc.getDocumentCatalog().getAcroForm();

        PDType0Font font = PDType0Font.load(doc, fontStream, false);
        String font_name = acroForm.getDefaultResources().add(font).getName();

        for (PDField field : acroForm.getFieldTree()) {
            if (field instanceof PDTextField) {
                PDTextField textField = (PDTextField) field;
                textField.getCOSObject().removeItem(COSName.MAX_LEN);
                textField.getCOSObject().setFlag(COSName.FF, FLAG_COMB, false);;
                textField.setDefaultAppearance(String.format("/%s 0 Tf 0 g", font_name));
                textField.getWidgets().forEach(w -> w.getAppearance().setNormalAppearance((PDAppearanceEntry)null));
                textField.setValue("Test");
            }
        }
        

        doc.save(new File(RESULT_FOLDER, "0-filledDropOldAppearanceNoCombNoMax.pdf"));
        doc.close();
    }        
}
 

/**
 * <a href="https://stackoverflow.com/questions/56938135/pdfbox-inconsistent-pdtextfield-autosize-behavior-after-setvalue">
 * PDFBox Inconsistent PDTextField Autosize Behavior after setValue
 * </a>
 * <br/>
 * <a href="http://www.filedropper.com/0postfontload">
 * 0.pdf
 * </a>
 * <p>
 * By resetting the MultiLine flags, too, one eventually gets rid
 * of the problem of the lower part of the field value being cut
 * off in the Care Providers Address fields. This actually should
 * be considered an issue of PDFBox, though, not of the source PDF
 * here.
 * </p>
 * @see #testFill0LikeXenyal()
 * @see #testFill0DropOldAppearance()
 * @see #testFill0DropOldAppearanceNoCombNoMax()
 */
@Test
public void testFill0DropOldAppearanceNoCombNoMaxNoMultiLine() throws IOException {
    final int FLAG_MULTILINE = 1 << 12;
    final int FLAG_COMB = 1 << 24;

    try (   InputStream originalStream = getClass().getResourceAsStream("0.pdf");
            InputStream fontStream = getClass().getResourceAsStream("Lato-Regular.ttf"))
    {
        PDDocument doc = Loader.loadPDF(originalStream);
        PDAcroForm acroForm = doc.getDocumentCatalog().getAcroForm();

        PDType0Font font = PDType0Font.load(doc, fontStream, false);
        String font_name = acroForm.getDefaultResources().add(font).getName();

        for (PDField field : acroForm.getFieldTree()) {
            if (field instanceof PDTextField) {
                PDTextField textField = (PDTextField) field;
                textField.getCOSObject().removeItem(COSName.MAX_LEN);
                textField.getCOSObject().setFlag(COSName.FF, FLAG_COMB | FLAG_MULTILINE, false);;
                textField.setDefaultAppearance(String.format("/%s 0 Tf 0 g", font_name));
                textField.getWidgets().forEach(w -> w.getAppearance().setNormalAppearance((PDAppearanceEntry)null));
                textField.setValue("Test");
            }
        }
        

        doc.save(new File(RESULT_FOLDER, "0-filledDropOldAppearanceNoCombNoMaxNoMultiLine.pdf"));
        doc.close();
    }        
}
 

/** @see #testCheckAcroFormGsa500Pdf_v4() */
boolean isFieldFilledAcroForm(PDAcroForm acroForm, String fieldName) throws IOException {
    for (PDField field : acroForm.getFieldTree()) {
        if (field instanceof PDPushButton && fieldName.equals(field.getPartialName())) {
            for (final PDAnnotationWidget widget : field.getWidgets()) {
                WidgetImageChecker checker = new WidgetImageChecker(widget);
                if (checker.hasImages())
                    return true;
            }
        }
    }
    return false;
}
 

/**
 * <a href="https://stackoverflow.com/questions/49427615/how-to-extract-label-text-from-push-button-using-apache-pdfbox">
 * How to extract label text from Push button using Apache PDFBox?
 * </a>
 * <p>
 * This method extracts the text from the normal appearance streams
 * of the form fields in the given PDF document.
 * </p>
 * @see #testBtn()
 * @see #testKYF211Beställning2014()
 */
public void showNormalFieldAppearanceTexts(PDDocument document) throws IOException {
    PDAcroForm acroForm = document.getDocumentCatalog().getAcroForm();

    if (acroForm != null) {
        SimpleXObjectTextStripper stripper = new SimpleXObjectTextStripper();

        for (PDField field : acroForm.getFieldTree()) {
            if (field instanceof PDTerminalField) {
                PDTerminalField terminalField = (PDTerminalField) field;
                System.out.println();
                System.out.println("* " + terminalField.getFullyQualifiedName());
                for (PDAnnotationWidget widget : terminalField.getWidgets()) {
                    PDAppearanceDictionary appearance = widget.getAppearance();
                    if (appearance != null) {
                        PDAppearanceEntry normal = appearance.getNormalAppearance();
                        if (normal != null) {
                            Map<COSName, PDAppearanceStream> streams = normal.isSubDictionary() ? normal.getSubDictionary() :
                                Collections.singletonMap(COSName.DEFAULT, normal.getAppearanceStream());
                            for (Map.Entry<COSName, PDAppearanceStream> entry : streams.entrySet()) {
                                String text = stripper.getText(entry.getValue());
                                System.out.printf("  * %s: %s\n", entry.getKey().getName(), text);
                            }
                        }
                    }
                }
            }
        }
    }
}