com.aspose.words

com.aspose.words

Class SpecialChar

  • java.lang.Object
Base class for special characters in the document.

A Microsoft Word document can include a number of special characters that represent fields, form fields, shapes, OLE objects, footnotes etc. For the list of special characters see ControlChar.

SpecialChar is an inline-node and can only be a child of Paragraph.

SpecialChar char is used as a base class for more specific classes that represent special characters that Aspose.Words provides programmatic access for. The SpecialChar class is also used itself to represent special character for which Aspose.Words does not provide detailed programmatic access.

Example:

Implements the Visitor Pattern to remove all content formatted as hidden from the document.
public void removeHiddenContentFromDocument() throws Exception {
    // Open the document we want to remove hidden content from.
    Document doc = new Document(getMyDir() + "Font.Hidden.doc");

    // Create an object that inherits from the DocumentVisitor class.
    RemoveHiddenContentVisitor hiddenContentRemover = new RemoveHiddenContentVisitor();

    // This is the well known Visitor pattern. Get the model to accept a visitor.
    // The model will iterate through itself by calling the corresponding methods
    // on the visitor object (this is called visiting).

    // We can run it over the entire the document like so:
    doc.accept(hiddenContentRemover);

    // Or we can run it on only a specific node.
    Paragraph para = (Paragraph) doc.getChild(NodeType.PARAGRAPH, 4, true);
    para.accept(hiddenContentRemover);

    // Or over a different type of node like below.
    Table table = (Table) doc.getChild(NodeType.TABLE, 0, true);
    table.accept(hiddenContentRemover);

    doc.save(getArtifactsDir() + "Font.Hidden.doc");

}

/**
 * This class when executed will remove all hidden content from the Document. Implemented as a Visitor.
 */
private class RemoveHiddenContentVisitor extends DocumentVisitor {
    /**
     * Called when a FieldStart node is encountered in the document.
     */
    public int visitFieldStart(final FieldStart fieldStart) throws Exception {
        // If this node is hidden, then remove it.
        if (isHidden(fieldStart)) {
            fieldStart.remove();
        }

        return VisitorAction.CONTINUE;
    }

    /**
     * Called when a FieldEnd node is encountered in the document.
     */
    public int visitFieldEnd(final FieldEnd fieldEnd) throws Exception {
        if (isHidden(fieldEnd)) {
            fieldEnd.remove();
        }

        return VisitorAction.CONTINUE;
    }

    /**
     * Called when a FieldSeparator node is encountered in the document.
     */
    public int visitFieldSeparator(final FieldSeparator fieldSeparator) throws Exception {
        if (isHidden(fieldSeparator)) {
            fieldSeparator.remove();
        }

        return VisitorAction.CONTINUE;
    }

    /**
     * Called when a Run node is encountered in the document.
     */
    public int visitRun(final Run run) throws Exception {
        if (isHidden(run)) {
            run.remove();
        }

        return VisitorAction.CONTINUE;
    }

    /**
     * Called when a Paragraph node is encountered in the document.
     */
    public int visitParagraphStart(final Paragraph paragraph) throws Exception {
        if (isHidden(paragraph)) {
            paragraph.remove();
        }

        return VisitorAction.CONTINUE;
    }

    /**
     * Called when a FormField is encountered in the document.
     */
    public int visitFormField(final FormField field) throws Exception {
        if (isHidden(field)) {
            field.remove();
        }

        return VisitorAction.CONTINUE;
    }

    /**
     * Called when a GroupShape is encountered in the document.
     */
    public int visitGroupShapeStart(final GroupShape groupShape) throws Exception {
        if (isHidden(groupShape)) {
            groupShape.remove();
        }

        return VisitorAction.CONTINUE;
    }

    /**
     * Called when a Shape is encountered in the document.
     */
    public int visitShapeStart(final Shape shape) throws Exception {
        if (isHidden(shape)) {
            shape.remove();
        }

        return VisitorAction.CONTINUE;
    }

    /**
     * Called when a Comment is encountered in the document.
     */
    public int visitCommentStart(final Comment comment) throws Exception {
        if (isHidden(comment)) {
            comment.remove();
        }

        return VisitorAction.CONTINUE;
    }

    /**
     * Called when a Footnote is encountered in the document.
     */
    public int visitFootnoteStart(final Footnote footnote) throws Exception {
        if (isHidden(footnote)) {
            footnote.remove();
        }

        return VisitorAction.CONTINUE;
    }

    /**
     * Called when visiting of a Table node is ended in the document.
     */
    public int visitTableEnd(final Table table) {
        // At the moment there is no way to tell if a particular Table/Row/Cell is hidden.
        // Instead, if the content of a table is hidden, then all inline child nodes of the table should be
        // hidden and thus removed by previous visits as well. This will result in the container being empty
        // so if this is the case we know to remove the table node.
        //
        // Note that a table which is not hidden but simply has no content will not be affected by this algorthim,
        // as technically they are not completely empty (for example a properly formed Cell will have at least
        // an empty paragraph in it)
        if (!table.hasChildNodes()) {
            table.remove();
        }

        return VisitorAction.CONTINUE;
    }

    /**
     * Called when visiting of a Cell node is ended in the document.
     */
    public int visitCellEnd(final Cell cell) {
        if (!cell.hasChildNodes() && cell.getParentNode() != null) {
            cell.remove();
        }

        return VisitorAction.CONTINUE;
    }

    /**
     * Called when visiting of a Row node is ended in the document.
     */
    public int visitRowEnd(final Row row) {
        if (!row.hasChildNodes() && row.getParentNode() != null) {
            row.remove();
        }

        return VisitorAction.CONTINUE;
    }

    /**
     * Called when a SpecialCharacter is encountered in the document.
     */
    public int visitSpecialChar(final SpecialChar character) throws Exception {
        if (isHidden(character)) {
            character.remove();
        }

        return VisitorAction.CONTINUE;
    }

    /**
     * Returns true if the node passed is set as hidden, returns false if it is visible.
     */
    private boolean isHidden(final Node node) {
        if (node instanceof Inline) {
            // If the node is Inline then cast it to retrieve the Font property which contains the hidden property
            Inline currentNode = (Inline) node;
            return currentNode.getFont().getHidden();
        } else if (node.getNodeType() == NodeType.PARAGRAPH) {
            // If the node is a paragraph cast it to retrieve the ParagraphBreakFont which contains the hidden property
            Paragraph para = (Paragraph) node;
            return para.getParagraphBreakFont().getHidden();
        } else if (node instanceof ShapeBase) {
            // Node is a shape or groupshape.
            ShapeBase shape = (ShapeBase) node;
            return shape.getFont().getHidden();
        } else if (node instanceof InlineStory) {
            // Node is a comment or footnote.
            InlineStory inlineStory = (InlineStory) node;
            return inlineStory.getFont().getHidden();
        }

        // A node that is passed to this method which does not contain a hidden property will end up here.
        // By default nodes are not hidden so return false.
        return false;
    }
}

Property Getters/Setters Summary
DocumentBasegetDocument()
Gets the document to which this node belongs.
FontgetFont()
Provides access to the font formatting of this object.
booleanisComposite()
Returns true if this node can contain other nodes.
booleanisDeleteRevision()
Returns true if this object was deleted in Microsoft Word while change tracking was enabled.
booleanisFormatRevision()
Returns true if formatting of the object was changed in Microsoft Word while change tracking was enabled.
booleanisInsertRevision()
Returns true if this object was inserted in Microsoft Word while change tracking was enabled.
booleanisMoveFromRevision()
Returns true if this object was moved (deleted) in Microsoft Word while change tracking was enabled.
booleanisMoveToRevision()
Returns true if this object was moved (inserted) in Microsoft Word while change tracking was enabled.
NodegetNextSibling()
Gets the node immediately following this node.
intgetNodeType()
Returns NodeType.SpecialChar. The value of the property is NodeType integer constant.
CompositeNodegetParentNode()
Gets the immediate parent of this node.
ParagraphgetParentParagraph()
Retrieves the parent Paragraph of this node.
NodegetPreviousSibling()
Gets the node immediately preceding this node.
RangegetRange()
Returns a Range object that represents the portion of a document that is contained in this node.
 
Method Summary
booleanaccept(DocumentVisitor visitor)
Accepts a visitor.
NodedeepClone(boolean isCloneChildren)
CompositeNodegetAncestor(int ancestorType)
Gets the first ancestor of the specified NodeType.
CompositeNodegetAncestor(java.lang.Class ancestorType)
Gets the first ancestor of the specified object type.
java.lang.StringgetText()
Gets the special character that this node represents.
NodenextPreOrder(Node rootNode)
Gets next node according to the pre-order tree traversal algorithm.
NodepreviousPreOrder(Node rootNode)
Gets the previous node according to the pre-order tree traversal algorithm.
voidremove()
Removes itself from the parent.
java.lang.StringtoString(SaveOptions saveOptions)
Exports the content of the node into a string using the specified save options.
java.lang.StringtoString(int saveFormat)
Exports the content of the node into a string in the specified format.
 

    • Property Getters/Setters Detail

      • getDocument

        public DocumentBase getDocument()
        Gets the document to which this node belongs.

        The node always belongs to a document even if it has just been created and not yet added to the tree, or if it has been removed from the tree.

        Example:

        Shows that when you create any node, it requires a document that will own the node.
        // Open a file from disk.
Document doc = new Document();

// Creating a new node of any type requires a document passed into the constructor.
Paragraph para = new Paragraph(doc);

// The new paragraph node does not yet have a parent.
System.out.println("Paragraph has no parent node: " + (para.getParentNode() == null));

// But the paragraph node knows its document.
System.out.println("Both nodes' documents are the same: " + (para.getDocument() == doc));

// The fact that a node always belongs to a document allows us to access and modify
// properties that reference the document-wide data such as styles or lists.
para.getParagraphFormat().setStyleName("Heading 1");

// Now add the paragraph to the main text of the first section.
doc.getFirstSection().getBody().appendChild(para);

// The paragraph node is now a child of the Body node.
System.out.println("Paragraph has a parent node: " + (para.getParentNode() != null));

      • getFont

        public Font getFont()
        Provides access to the font formatting of this object.

        Example:

        Creates a simple document from scratch using the Aspose.Words object model.
        // Create an "empty" document. Note that like in Microsoft Word,
// the empty document has one section, body and one paragraph in it.
Document doc = new Document();

// This truly makes the document empty. No sections (not possible in Microsoft Word).
doc.removeAllChildren();

// Create a new section node.
// Note that the section has not yet been added to the document,
// but we have to specify the parent document.
Section section = new Section(doc);

// Append the section to the document.
doc.appendChild(section);

// Lets set some properties for the section.
section.getPageSetup().setSectionStart(SectionStart.NEW_PAGE);
section.getPageSetup().setPaperSize(PaperSize.LETTER);

// The section that we created is empty, lets populate it. The section needs at least the Body node.
Body body = new Body(doc);
section.appendChild(body);

// The body needs to have at least one paragraph.
// Note that the paragraph has not yet been added to the document,
// but we have to specify the parent document.
// The parent document is needed so the paragraph can correctly work
// with styles and other document-wide information.
Paragraph para = new Paragraph(doc);
body.appendChild(para);

// We can set some formatting for the paragraph
para.getParagraphFormat().setStyleName("Heading 1");
para.getParagraphFormat().setAlignment(ParagraphAlignment.CENTER);

// So far we have one empty paragraph in the document.
// The document is valid and can be saved, but lets add some text before saving.
// Create a new run of text and add it to our paragraph.
Run run = new Run(doc);
run.setText("Hello World!");
run.getFont().setColor(Color.RED);
para.appendChild(run);

// As a matter of interest, you can retrieve text of the whole document and
// see that \x000c is automatically appended. \x000c is the end of section character.
System.out.println(doc.getText());

// Save the document.
doc.save(getArtifactsDir() + "Section.CreateFromScratch.doc");

      • isComposite

        public boolean isComposite()
        Returns true if this node can contain other nodes. This method returns false as Node cannot have child nodes.

        Example:

        Shows how to efficiently visit all direct and indirect children of a composite node.
        public void recurseAllNodes() throws Exception {
    // Open a document.
    Document doc = new Document(getMyDir() + "Node.RecurseAllNodes.doc");

    // Invoke the recursive function that will walk the tree.
    traverseAllNodes(doc);
}

/**
 * A simple function that will walk through all children of a specified node recursively
 * and print the type of each node to the screen.
 */
@Test(enabled = false)
public void traverseAllNodes(final CompositeNode parentNode) {
    // This is the most efficient way to loop through immediate children of a node.
    for (Node childNode = parentNode.getFirstChild(); childNode != null; childNode = childNode.getNextSibling()) {
        // Do some useful work.
        System.out.println(Node.nodeTypeToString(childNode.getNodeType()));

        // Recurse into the node if it is a composite node.
        if (childNode.isComposite()) {
            traverseAllNodes((CompositeNode) childNode);
        }
    }
}

      • isDeleteRevision

        public boolean isDeleteRevision()
        Returns true if this object was deleted in Microsoft Word while change tracking was enabled.

        Example:

        Shows how to process revision-related properties of Inline nodes.
        Document doc = new Document(getMyDir() + "Inline.Revisions.docx");

// This document has 6 revisions
Assert.assertEquals(doc.getRevisions().getCount(), 6);

// The parent node of a revision is the run that the revision concerns, which is an Inline node
Run run = (Run) doc.getRevisions().get(0).getParentNode();

// Get the parent paragraph
Paragraph firstParagraph = run.getParentParagraph();
RunCollection runs = firstParagraph.getRuns();

Assert.assertEquals(runs.getCount(), 6);

// The text in the run at index #2 was typed after revisions were tracked, so it will count as an insert revision
// The font was changed, so it will also be a format revision
Assert.assertTrue(runs.get(2).isInsertRevision());
Assert.assertTrue(runs.get(2).isFormatRevision());

// If one node was moved from one place to another while changes were tracked,
// the node will be placed at the departure location as a "move to revision",
// and a "move from revision" node will be left behind at the origin, in case we want to reject changes
// Highlighting text and dragging it to another place with the mouse and cut-and-pasting (but not copy-pasting) both count as "move revisions"
// The node with the "IsMoveToRevision" flag is the arrival of the move operation, and the node with the "IsMoveFromRevision" flag is the departure point
Assert.assertTrue(runs.get(1).isMoveToRevision());
Assert.assertTrue(runs.get(4).isMoveFromRevision());

// If an Inline node gets deleted while changes are being tracked, it will leave behind a node with the IsDeleteRevision flag set to true until changes are accepted
Assert.assertTrue(runs.get(5).isDeleteRevision());

      • isFormatRevision

        public boolean isFormatRevision()
        Returns true if formatting of the object was changed in Microsoft Word while change tracking was enabled.

        Example:

        Shows how to process revision-related properties of Inline nodes.
        Document doc = new Document(getMyDir() + "Inline.Revisions.docx");

// This document has 6 revisions
Assert.assertEquals(doc.getRevisions().getCount(), 6);

// The parent node of a revision is the run that the revision concerns, which is an Inline node
Run run = (Run) doc.getRevisions().get(0).getParentNode();

// Get the parent paragraph
Paragraph firstParagraph = run.getParentParagraph();
RunCollection runs = firstParagraph.getRuns();

Assert.assertEquals(runs.getCount(), 6);

// The text in the run at index #2 was typed after revisions were tracked, so it will count as an insert revision
// The font was changed, so it will also be a format revision
Assert.assertTrue(runs.get(2).isInsertRevision());
Assert.assertTrue(runs.get(2).isFormatRevision());

// If one node was moved from one place to another while changes were tracked,
// the node will be placed at the departure location as a "move to revision",
// and a "move from revision" node will be left behind at the origin, in case we want to reject changes
// Highlighting text and dragging it to another place with the mouse and cut-and-pasting (but not copy-pasting) both count as "move revisions"
// The node with the "IsMoveToRevision" flag is the arrival of the move operation, and the node with the "IsMoveFromRevision" flag is the departure point
Assert.assertTrue(runs.get(1).isMoveToRevision());
Assert.assertTrue(runs.get(4).isMoveFromRevision());

// If an Inline node gets deleted while changes are being tracked, it will leave behind a node with the IsDeleteRevision flag set to true until changes are accepted
Assert.assertTrue(runs.get(5).isDeleteRevision());

      • isInsertRevision

        public boolean isInsertRevision()
        Returns true if this object was inserted in Microsoft Word while change tracking was enabled.

        Example:

        Shows how to process revision-related properties of Inline nodes.
        Document doc = new Document(getMyDir() + "Inline.Revisions.docx");

// This document has 6 revisions
Assert.assertEquals(doc.getRevisions().getCount(), 6);

// The parent node of a revision is the run that the revision concerns, which is an Inline node
Run run = (Run) doc.getRevisions().get(0).getParentNode();

// Get the parent paragraph
Paragraph firstParagraph = run.getParentParagraph();
RunCollection runs = firstParagraph.getRuns();

Assert.assertEquals(runs.getCount(), 6);

// The text in the run at index #2 was typed after revisions were tracked, so it will count as an insert revision
// The font was changed, so it will also be a format revision
Assert.assertTrue(runs.get(2).isInsertRevision());
Assert.assertTrue(runs.get(2).isFormatRevision());

// If one node was moved from one place to another while changes were tracked,
// the node will be placed at the departure location as a "move to revision",
// and a "move from revision" node will be left behind at the origin, in case we want to reject changes
// Highlighting text and dragging it to another place with the mouse and cut-and-pasting (but not copy-pasting) both count as "move revisions"
// The node with the "IsMoveToRevision" flag is the arrival of the move operation, and the node with the "IsMoveFromRevision" flag is the departure point
Assert.assertTrue(runs.get(1).isMoveToRevision());
Assert.assertTrue(runs.get(4).isMoveFromRevision());

// If an Inline node gets deleted while changes are being tracked, it will leave behind a node with the IsDeleteRevision flag set to true until changes are accepted
Assert.assertTrue(runs.get(5).isDeleteRevision());

      • isMoveFromRevision

        public boolean isMoveFromRevision()
        Returns true if this object was moved (deleted) in Microsoft Word while change tracking was enabled.

        Example:

        Shows how to process revision-related properties of Inline nodes.
        Document doc = new Document(getMyDir() + "Inline.Revisions.docx");

// This document has 6 revisions
Assert.assertEquals(doc.getRevisions().getCount(), 6);

// The parent node of a revision is the run that the revision concerns, which is an Inline node
Run run = (Run) doc.getRevisions().get(0).getParentNode();

// Get the parent paragraph
Paragraph firstParagraph = run.getParentParagraph();
RunCollection runs = firstParagraph.getRuns();

Assert.assertEquals(runs.getCount(), 6);

// The text in the run at index #2 was typed after revisions were tracked, so it will count as an insert revision
// The font was changed, so it will also be a format revision
Assert.assertTrue(runs.get(2).isInsertRevision());
Assert.assertTrue(runs.get(2).isFormatRevision());

// If one node was moved from one place to another while changes were tracked,
// the node will be placed at the departure location as a "move to revision",
// and a "move from revision" node will be left behind at the origin, in case we want to reject changes
// Highlighting text and dragging it to another place with the mouse and cut-and-pasting (but not copy-pasting) both count as "move revisions"
// The node with the "IsMoveToRevision" flag is the arrival of the move operation, and the node with the "IsMoveFromRevision" flag is the departure point
Assert.assertTrue(runs.get(1).isMoveToRevision());
Assert.assertTrue(runs.get(4).isMoveFromRevision());

// If an Inline node gets deleted while changes are being tracked, it will leave behind a node with the IsDeleteRevision flag set to true until changes are accepted
Assert.assertTrue(runs.get(5).isDeleteRevision());

      • isMoveToRevision

        public boolean isMoveToRevision()
        Returns true if this object was moved (inserted) in Microsoft Word while change tracking was enabled.

        Example:

        Shows how to process revision-related properties of Inline nodes.
        Document doc = new Document(getMyDir() + "Inline.Revisions.docx");

// This document has 6 revisions
Assert.assertEquals(doc.getRevisions().getCount(), 6);

// The parent node of a revision is the run that the revision concerns, which is an Inline node
Run run = (Run) doc.getRevisions().get(0).getParentNode();

// Get the parent paragraph
Paragraph firstParagraph = run.getParentParagraph();
RunCollection runs = firstParagraph.getRuns();

Assert.assertEquals(runs.getCount(), 6);

// The text in the run at index #2 was typed after revisions were tracked, so it will count as an insert revision
// The font was changed, so it will also be a format revision
Assert.assertTrue(runs.get(2).isInsertRevision());
Assert.assertTrue(runs.get(2).isFormatRevision());

// If one node was moved from one place to another while changes were tracked,
// the node will be placed at the departure location as a "move to revision",
// and a "move from revision" node will be left behind at the origin, in case we want to reject changes
// Highlighting text and dragging it to another place with the mouse and cut-and-pasting (but not copy-pasting) both count as "move revisions"
// The node with the "IsMoveToRevision" flag is the arrival of the move operation, and the node with the "IsMoveFromRevision" flag is the departure point
Assert.assertTrue(runs.get(1).isMoveToRevision());
Assert.assertTrue(runs.get(4).isMoveFromRevision());

// If an Inline node gets deleted while changes are being tracked, it will leave behind a node with the IsDeleteRevision flag set to true until changes are accepted
Assert.assertTrue(runs.get(5).isDeleteRevision());

      • getNextSibling

        public Node getNextSibling()
        Gets the node immediately following this node. If there is no next node, a null is returned.

        Example:

        Shows how to enumerate immediate child nodes of a composite node using NextSibling. In this example we enumerate all paragraphs of a section body.
        // Get the section that we want to work on.
Section section = doc.getSections().get(0);
Body body = section.getBody();

// Loop starting from the first child until we reach null.
for (Node node = body.getFirstChild(); node != null; node = node.getNextSibling()) {
    // Output the types of the nodes that we come across.
    System.out.println(Node.nodeTypeToString(node.getNodeType()));
}

        Example:

        Shows how to efficiently visit all direct and indirect children of a composite node.
        public void recurseAllNodes() throws Exception {
    // Open a document.
    Document doc = new Document(getMyDir() + "Node.RecurseAllNodes.doc");

    // Invoke the recursive function that will walk the tree.
    traverseAllNodes(doc);
}

/**
 * A simple function that will walk through all children of a specified node recursively
 * and print the type of each node to the screen.
 */
@Test(enabled = false)
public void traverseAllNodes(final CompositeNode parentNode) {
    // This is the most efficient way to loop through immediate children of a node.
    for (Node childNode = parentNode.getFirstChild(); childNode != null; childNode = childNode.getNextSibling()) {
        // Do some useful work.
        System.out.println(Node.nodeTypeToString(childNode.getNodeType()));

        // Recurse into the node if it is a composite node.
        if (childNode.isComposite()) {
            traverseAllNodes((CompositeNode) childNode);
        }
    }
}

      • getNodeType

        public int getNodeType()
        Returns NodeType.SpecialChar. The value of the property is NodeType integer constant.

        Example:

        Shows how to retrieve the NodeType enumeration of nodes.
        Document doc = new Document(getMyDir() + "Document.doc");

// Let's pick a node that we can't be quite sure of what type it is.
// In this case lets pick the first node of the first paragraph in the body of the document
Node node = doc.getFirstSection().getBody().getFirstParagraph().getFirstChild();
System.out.println("NodeType of first child: " + Node.nodeTypeToString(node.getNodeType()));

// This time let's pick a node that we know the type of. Create a new paragraph and a table node.
Paragraph para = new Paragraph(doc);
Table table = new Table(doc);

// Access to NodeType for typed nodes will always return their specific NodeType.
// i.e A paragraph node will always return NodeType.Paragraph, a table node will always return NodeType.Table.
System.out.println("NodeType of Paragraph: " + Node.nodeTypeToString(para.getNodeType()));
System.out.println("NodeType of Table: " + Node.nodeTypeToString(table.getNodeType()));

      • getParentNode

        public CompositeNode getParentNode()
        Gets the immediate parent of this node.

        If a node has just been created and not yet added to the tree, or if it has been removed from the tree, the parent is null.

        Example:

        Shows how to access the parent node.
        // Create a new empty document. It has one section.
Document doc = new Document();

// The section is the first child node of the document.
Node section = doc.getFirstChild();

// The section's parent node is the document.
System.out.println("Section parent is the document: " + (doc == section.getParentNode()));

        Example:

        Shows that when you create any node, it requires a document that will own the node.
        // Open a file from disk.
Document doc = new Document();

// Creating a new node of any type requires a document passed into the constructor.
Paragraph para = new Paragraph(doc);

// The new paragraph node does not yet have a parent.
System.out.println("Paragraph has no parent node: " + (para.getParentNode() == null));

// But the paragraph node knows its document.
System.out.println("Both nodes' documents are the same: " + (para.getDocument() == doc));

// The fact that a node always belongs to a document allows us to access and modify
// properties that reference the document-wide data such as styles or lists.
para.getParagraphFormat().setStyleName("Heading 1");

// Now add the paragraph to the main text of the first section.
doc.getFirstSection().getBody().appendChild(para);

// The paragraph node is now a child of the Body node.
System.out.println("Paragraph has a parent node: " + (para.getParentNode() != null));

      • getParentParagraph

        public Paragraph getParentParagraph()
        Retrieves the parent Paragraph of this node.

        Example:

        Shows how to process revision-related properties of Inline nodes.
        Document doc = new Document(getMyDir() + "Inline.Revisions.docx");

// This document has 6 revisions
Assert.assertEquals(doc.getRevisions().getCount(), 6);

// The parent node of a revision is the run that the revision concerns, which is an Inline node
Run run = (Run) doc.getRevisions().get(0).getParentNode();

// Get the parent paragraph
Paragraph firstParagraph = run.getParentParagraph();
RunCollection runs = firstParagraph.getRuns();

Assert.assertEquals(runs.getCount(), 6);

// The text in the run at index #2 was typed after revisions were tracked, so it will count as an insert revision
// The font was changed, so it will also be a format revision
Assert.assertTrue(runs.get(2).isInsertRevision());
Assert.assertTrue(runs.get(2).isFormatRevision());

// If one node was moved from one place to another while changes were tracked,
// the node will be placed at the departure location as a "move to revision",
// and a "move from revision" node will be left behind at the origin, in case we want to reject changes
// Highlighting text and dragging it to another place with the mouse and cut-and-pasting (but not copy-pasting) both count as "move revisions"
// The node with the "IsMoveToRevision" flag is the arrival of the move operation, and the node with the "IsMoveFromRevision" flag is the departure point
Assert.assertTrue(runs.get(1).isMoveToRevision());
Assert.assertTrue(runs.get(4).isMoveFromRevision());

// If an Inline node gets deleted while changes are being tracked, it will leave behind a node with the IsDeleteRevision flag set to true until changes are accepted
Assert.assertTrue(runs.get(5).isDeleteRevision());

      • getPreviousSibling

        public Node getPreviousSibling()
        Gets the node immediately preceding this node. If there is no preceding node, a null is returned.

        Example:

        Demonstrates use of methods of Node and CompositeNode to remove a section before the last section in the document.
        // Document is a CompositeNode and LastChild returns the last child node in the Document node.
// Since the Document can contain only Section nodes, the last child is the last section.
Node lastSection = doc.getLastChild();

// Each node knows its next and previous sibling nodes.
// Previous sibling of a section is a section before the specified section.
// If the node is the first child, PreviousSibling will return null.
Node sectionBeforeLast = lastSection.getPreviousSibling();

if (sectionBeforeLast != null) {
    doc.removeChild(sectionBeforeLast);
}

      • getRange

        public Range getRange()
        Returns a Range object that represents the portion of a document that is contained in this node.

        Example:

        Shows how to delete all characters of a range.
        // Open Word document.
Document doc = new Document(getMyDir() + "Range.DeleteSection.doc");

// The document contains two sections. Each section has a paragraph of text.
System.out.println(doc.getText());

// Delete the first section from the document.
doc.getSections().get(0).getRange().delete();

// Check the first section was deleted by looking at the text of the whole document again.
System.out.println(doc.getText());

    • Method Detail

      • accept

        public boolean accept(DocumentVisitor visitor)
              throws java.lang.Exception
        Accepts a visitor.

        Calls DocumentVisitor.VisitSpecialChar.

        For more info see the Visitor design pattern.

        Parameters:
        visitor - The visitor that will visit the node.
        Returns:
        False if the visitor requested the enumeration to stop.

      • deepClone

        public Node deepClone(boolean isCloneChildren)

        Example:

        Shows how to clone composite nodes with and without their child nodes.
        // Create a new empty document.
Document doc = new Document();

// Add some text to the first paragraph
Paragraph para = doc.getFirstSection().getBody().getFirstParagraph();
para.appendChild(new Run(doc, "Some text"));

// Clone the paragraph and the child nodes.
Node cloneWithChildren = para.deepClone(true);
// Only clone the paragraph and no child nodes.
Node cloneWithoutChildren = para.deepClone(false);

      • getAncestor

        public CompositeNode getAncestor(int ancestorType)
        Gets the first ancestor of the specified NodeType.
        Parameters:
        ancestorType - A NodeType value. The node type of the ancestor to retrieve.
        Returns:
        The ancestor of the specified type or null if no ancestor of this type was found.

        Example:

        Shows how to find out if a table contains another table or if the table itself is nested inside another table.
        public void calculateDepthOfNestedTables() throws Exception {
    Document doc = new Document(getMyDir() + "Table.NestedTables.doc");
    int tableIndex = 0;

    for (Table table : (Iterable<Table>) doc.getChildNodes(NodeType.TABLE, true)) {
        // First lets find if any cells in the table have tables themselves as children.
        int count = getChildTableCount(table);
        System.out.println(MessageFormat.format("Table #{0} has {1} tables directly within its cells", tableIndex, count));

        // Now let's try the other way around, lets try find if the table is nested inside another table and at what depth.
        int tableDepth = getNestedDepthOfTable(table);

        if (tableDepth > 0) {
            System.out.println(MessageFormat.format("Table #{0} is nested inside another table at depth of {1}", tableIndex, tableDepth));
        } else {
            System.out.println(MessageFormat.format("Table #{0} is a non nested table (is not a child of another table)", tableIndex));
        }

        tableIndex++;
    }
}

/**
 * Calculates what level a table is nested inside other tables.
 *
 * @returns An integer containing the level the table is nested at.
 * 0 = Table is not nested inside any other table
 * 1 = Table is nested within one parent table
 * 2 = Table is nested within two parent tables etc..
 */
private static int getNestedDepthOfTable(final Table table) {
    int depth = 0;

    int type = table.getNodeType();
    // The parent of the table will be a Cell, instead attempt to find a grandparent that is of type Table
    Node parent = table.getAncestor(table.getNodeType());

    while (parent != null) {
        // Every time we find a table a level up we increase the depth counter and then try to find an
        // ancestor of type table from the parent.
        depth++;
        parent = parent.getAncestor(Table.class);
    }

    return depth;
}

/**
 * Determines if a table contains any immediate child table within its cells.
 * Does not recursively traverse through those tables to check for further tables.
 *
 * @returns Returns true if at least one child cell contains a table.
 * Returns false if no cells in the table contains a table.
 */
private static int getChildTableCount(final Table table) {
    int tableCount = 0;
    // Iterate through all child rows in the table
    for (Row row : table.getRows()) {
        // Iterate through all child cells in the row
        for (Cell cell : row.getCells()) {
            // Retrieve the collection of child tables of this cell
            TableCollection childTables = cell.getTables();

            // If this cell has a table as a child then return true
            if (childTables.getCount() > 0) tableCount++;
        }
    }

    // No cell contains a table
    return tableCount;
}

      • getAncestor

        public CompositeNode getAncestor(java.lang.Class ancestorType)
        Gets the first ancestor of the specified object type.

        The ancestor type matches if it is equal to ancestorType or derived from ancestorType.

        Parameters:
        ancestorType - The object type of the ancestor to retrieve.
        Returns:
        The ancestor of the specified type or null if no ancestor of this type was found.

        Example:

        Shows how to find out if a table contains another table or if the table itself is nested inside another table.
        public void calculateDepthOfNestedTables() throws Exception {
    Document doc = new Document(getMyDir() + "Table.NestedTables.doc");
    int tableIndex = 0;

    for (Table table : (Iterable<Table>) doc.getChildNodes(NodeType.TABLE, true)) {
        // First lets find if any cells in the table have tables themselves as children.
        int count = getChildTableCount(table);
        System.out.println(MessageFormat.format("Table #{0} has {1} tables directly within its cells", tableIndex, count));

        // Now let's try the other way around, lets try find if the table is nested inside another table and at what depth.
        int tableDepth = getNestedDepthOfTable(table);

        if (tableDepth > 0) {
            System.out.println(MessageFormat.format("Table #{0} is nested inside another table at depth of {1}", tableIndex, tableDepth));
        } else {
            System.out.println(MessageFormat.format("Table #{0} is a non nested table (is not a child of another table)", tableIndex));
        }

        tableIndex++;
    }
}

/**
 * Calculates what level a table is nested inside other tables.
 *
 * @returns An integer containing the level the table is nested at.
 * 0 = Table is not nested inside any other table
 * 1 = Table is nested within one parent table
 * 2 = Table is nested within two parent tables etc..
 */
private static int getNestedDepthOfTable(final Table table) {
    int depth = 0;

    int type = table.getNodeType();
    // The parent of the table will be a Cell, instead attempt to find a grandparent that is of type Table
    Node parent = table.getAncestor(table.getNodeType());

    while (parent != null) {
        // Every time we find a table a level up we increase the depth counter and then try to find an
        // ancestor of type table from the parent.
        depth++;
        parent = parent.getAncestor(Table.class);
    }

    return depth;
}

/**
 * Determines if a table contains any immediate child table within its cells.
 * Does not recursively traverse through those tables to check for further tables.
 *
 * @returns Returns true if at least one child cell contains a table.
 * Returns false if no cells in the table contains a table.
 */
private static int getChildTableCount(final Table table) {
    int tableCount = 0;
    // Iterate through all child rows in the table
    for (Row row : table.getRows()) {
        // Iterate through all child cells in the row
        for (Cell cell : row.getCells()) {
            // Retrieve the collection of child tables of this cell
            TableCollection childTables = cell.getTables();

            // If this cell has a table as a child then return true
            if (childTables.getCount() > 0) tableCount++;
        }
    }

    // No cell contains a table
    return tableCount;
}

      • getText

        public java.lang.String getText()
        Gets the special character that this node represents.
        Returns:
        The string that contains the character that this node represents.

      • nextPreOrder

        public Node nextPreOrder(Node rootNode)
        Gets next node according to the pre-order tree traversal algorithm.
        Parameters:
        rootNode - The top node (limit) of traversal.
        Returns:
        Next node in pre-order order. Null if reached the rootNode.

        Example:

        Shows how to delete all images from a document using pre-order tree traversal.
        Node curNode = doc;
while (curNode != null) {
    Node nextNode = curNode.nextPreOrder(doc);

    if (curNode.previousPreOrder(doc) != null && nextNode != null) {
        Assert.assertEquals(curNode, nextNode.previousPreOrder(doc));
    }

    if (curNode.getNodeType() == NodeType.SHAPE) {
        Shape shape = (Shape) curNode;

        // Several shape types can have an image including image shapes and OLE objects.
        if (shape.hasImage()) {
            shape.remove();
        }
    }

    curNode = nextNode;
}

      • previousPreOrder

        public Node previousPreOrder(Node rootNode)
        Gets the previous node according to the pre-order tree traversal algorithm.
        Parameters:
        rootNode - The top node (limit) of traversal.
        Returns:
        Previous node in pre-order order. Null if reached the rootNode.

        Example:

        Shows how to delete all images from a document using pre-order tree traversal.
        Node curNode = doc;
while (curNode != null) {
    Node nextNode = curNode.nextPreOrder(doc);

    if (curNode.previousPreOrder(doc) != null && nextNode != null) {
        Assert.assertEquals(curNode, nextNode.previousPreOrder(doc));
    }

    if (curNode.getNodeType() == NodeType.SHAPE) {
        Shape shape = (Shape) curNode;

        // Several shape types can have an image including image shapes and OLE objects.
        if (shape.hasImage()) {
            shape.remove();
        }
    }

    curNode = nextNode;
}

      • remove

        public void remove()
        Removes itself from the parent.

        Example:

        Shows how to remove all nodes of a specific type from a composite node. In this example we remove tables from a section body.
        // Get the section that we want to work on.
Section section = doc.getSections().get(0);
Body body = section.getBody();

// Select the first child node in the body.
Node curNode = body.getFirstChild();

while (curNode != null) {
    // Save the pointer to the next sibling node because if the current
    // node is removed from the parent in the next step, we will have
    // no way of finding the next node to continue the loop.
    Node nextNode = curNode.getNextSibling();

    // A section body can contain Paragraph and Table nodes.
    // If the node is a Table, remove it from the parent.
    if (curNode.getNodeType() == NodeType.TABLE) {
        curNode.remove();
    }

    // Continue going through child nodes until null (no more siblings) is reached.
    curNode = nextNode;
}

        Example:

        Shows how to delete all images from a document.
        // Here we get all shapes from the document node, but you can do this for any smaller
// node too, for example delete shapes from a single section or a paragraph.
NodeCollection shapes = doc.getChildNodes(NodeType.SHAPE, true);

// We cannot delete shape nodes while we enumerate through the collection.
// One solution is to add nodes that we want to delete to a temporary array and delete afterwards.
ArrayList shapesToDelete = new ArrayList();
for (Shape shape : (Iterable<Shape>) shapes) {
    // Several shape types can have an image including image shapes and OLE objects.
    if (shape.hasImage()) {
        shapesToDelete.add(shape);
    }
}

// Now we can delete shapes.
for (Shape shape : (Iterable<Shape>) shapesToDelete) {
    shape.remove();
}

      • toString

        public java.lang.String toString(SaveOptions saveOptions)
               throws java.lang.Exception
        Exports the content of the node into a string using the specified save options.
        Parameters:
        saveOptions - Specifies the options that control how the node is saved.
        Returns:
        The content of the node in the specified format.

        Example:

        Exports the content of a node to string in HTML format using custom specified options.
        Document doc = new Document(getMyDir() + "Document.doc");

// Extract the last paragraph in the document to convert to HTML.
Node node = doc.getLastSection().getBody().getLastParagraph();

// Create an instance of HtmlSaveOptions and set a few options.
HtmlSaveOptions saveOptions = new HtmlSaveOptions();
saveOptions.setExportHeadersFootersMode(ExportHeadersFootersMode.PER_SECTION);
saveOptions.setExportRelativeFontSize(true);

// Convert the document to HTML and return as a string. Pass the instance of HtmlSaveOptions to
// to use the specified options during the conversion.
String nodeAsHtml = node.toString(saveOptions);

      • toString

        public java.lang.String toString(int saveFormat)
               throws java.lang.Exception
        Exports the content of the node into a string in the specified format.
        Returns:
        The content of the node in the specified format.
        Parameters:
        saveFormat - A SaveFormat value.

        Example:

        Shows how to extract the label of each paragraph in a list as a value or a String.
        Document doc = new Document(getMyDir() + "Lists.PrintOutAllLists.doc");
doc.updateListLabels();
int listParaCount = 1;

for (Paragraph paragraph : (Iterable<Paragraph>) doc.getChildNodes(NodeType.PARAGRAPH, true)) {
    // Find if we have the paragraph list. In our document our list uses plain arabic numbers,
    // which start at three and ends at six.
    if (paragraph.getListFormat().isListItem()) {
        System.out.println(MessageFormat.format("Paragraph #{0}", listParaCount));

        // This is the text we get when actually getting when we output this node to text format.
        // The list labels are not included in this text output. Trim any paragraph formatting characters.
        String paragraphText = paragraph.toString(SaveFormat.TEXT).trim();
        System.out.println("Exported Text: " + paragraphText);

        ListLabel label = paragraph.getListLabel();
        // This gets the position of the paragraph in current level of the list. If we have a list with multiple level then this
        // will tell us what position it is on that particular level.
        System.out.println("Numerical Id: " + label.getLabelValue());

        // Combine them together to include the list label with the text in the output.
        System.out.println("List label combined with text: " + label.getLabelString() + " " + paragraphText);

        listParaCount++;
    }
}

        Example:

        Shows the difference between calling the GetText and ToString methods on a node.
        Document doc = new Document();

// Enter a dummy field into the document.
DocumentBuilder builder = new DocumentBuilder(doc);
builder.insertField("MERGEFIELD Field");

// GetText will retrieve all field codes and special characters
System.out.println("GetText() Result: " + doc.getText());

// ToString will export the node to the specified format. When converted to text it will not retrieve fields code
// or special characters, but will still contain some natural formatting characters such as paragraph markers etc.
// This is the same as "viewing" the document as if it was opened in a text editor.
System.out.println("ToString() Result: " + doc.toString(SaveFormat.TEXT));

        Example:

        Exports the content of a node to string in HTML format using default options.
        Document doc = new Document(getMyDir() + "Document.doc");

// Extract the last paragraph in the document to convert to HTML.
Node node = doc.getLastSection().getBody().getLastParagraph();

// When ToString is called using the SaveFormat overload then conversion is executed using default save options.
// When saving to HTML using default options the following settings are set:
//   ExportImagesAsBase64 = true
//   CssStyleSheetType = CssStyleSheetType.Inline
//   ExportFontResources = false
String nodeAsHtml = node.toString(SaveFormat.HTML);