com.aspose.words
Class Node

java.lang.Object
    com.aspose.words.Node

All Implemented Interfaces:

java.lang.Cloneable

Direct Known Subclasses:

BookmarkEnd, BookmarkStart, CommentRangeEnd, CommentRangeStart, CompositeNode, EditableRangeEnd, EditableRangeStart, Inline, StructuredDocumentTagRangeEnd, StructuredDocumentTagRangeStart, SubDocument

public abstract class Node 
extends java.lang.Object

Document doc = new Document();

Paragraph paragraph = (Paragraph) doc.getChild(NodeType.PARAGRAPH, 0, true);
paragraph.appendChild(new Run(doc, "Hello world!"));
paragraph.appendChild(new Run(doc, " Hello again!"));

NodeCollection children = paragraph.getChildNodes();

// Paragraph may contain children of various types such as runs, shapes and so on
for (Node child : (Iterable<Node>) children)
    if (((child.getNodeType()) == (NodeType.RUN))) {
        Run run = (Run) child;
        System.out.println(run.getText());
    }

Document doc = new Document();
Paragraph para = doc.getFirstSection().getBody().getFirstParagraph();
para.appendChild(new Run(doc, "Hello world!"));

// Clone the paragraph and the child nodes
Node cloneWithChildren = para.deepClone(true);

Assert.assertTrue(((CompositeNode) cloneWithChildren).hasChildNodes());
Assert.assertEquals("Hello world!", cloneWithChildren.getText().trim());

// Clone the paragraph without its clild nodes
Node cloneWithoutChildren = para.deepClone(false);

Assert.assertFalse(((CompositeNode) cloneWithoutChildren).hasChildNodes());
Assert.assertEquals("", cloneWithoutChildren.getText().trim());

Document doc = new Document(getMyDir() + "Tables.docx");

Assert.assertEquals(2, doc.getChildNodes(NodeType.TABLE, true).getCount());

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

while (curNode != null) {
    // Save the next sibling node as a variable in case we want to move to it after deleting this node
    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;
}

Assert.assertEquals(0, doc.getChildNodes(NodeType.TABLE, true).getCount());

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 how to create a node and set its owning document.

// 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));

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 {
    Document doc = new Document(getMyDir() + "Paragraphs.docx");

    // Any node that can contain child nodes, such as the document itself, is composite
    Assert.assertTrue(doc.isComposite());

    // Invoke the recursive function that will go through and print all the child nodes of a composite node
    traverseAllNodes(doc, 0);
}

/// <summary>
/// Recursively traverses a node tree while printing the type of each node with an indent depending on depth as well as the contents of all inline nodes.
/// </summary>
@Test(enabled = false)
public void traverseAllNodes(CompositeNode parentNode, int depth) {
    // Loop through immediate children of a node
    for (Node childNode = parentNode.getFirstChild(); childNode != null; childNode = childNode.getNextSibling()) {
        System.out.println(MessageFormat.format("{0}{1}", String.format("    ", depth), Node.nodeTypeToString(childNode.getNodeType())));

        // Recurse into the node if it is a composite node
        if (childNode.isComposite()) {
            System.out.println();
            traverseAllNodes((CompositeNode) childNode, depth + 1);
        } else if (childNode instanceof Inline) {
            System.out.println(" - \"{childNode.GetText().Trim()}\"");
        } else {
            System.out.println();
        }
    }
}

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.

Document doc = new Document(getMyDir() + "Paragraphs.docx");

// Loop starting from the first child until we reach null
for (Node node = doc.getFirstSection().getBody().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 {
    Document doc = new Document(getMyDir() + "Paragraphs.docx");

    // Any node that can contain child nodes, such as the document itself, is composite
    Assert.assertTrue(doc.isComposite());

    // Invoke the recursive function that will go through and print all the child nodes of a composite node
    traverseAllNodes(doc, 0);
}

/// <summary>
/// Recursively traverses a node tree while printing the type of each node with an indent depending on depth as well as the contents of all inline nodes.
/// </summary>
@Test(enabled = false)
public void traverseAllNodes(CompositeNode parentNode, int depth) {
    // Loop through immediate children of a node
    for (Node childNode = parentNode.getFirstChild(); childNode != null; childNode = childNode.getNextSibling()) {
        System.out.println(MessageFormat.format("{0}{1}", String.format("    ", depth), Node.nodeTypeToString(childNode.getNodeType())));

        // Recurse into the node if it is a composite node
        if (childNode.isComposite()) {
            System.out.println();
            traverseAllNodes((CompositeNode) childNode, depth + 1);
        } else if (childNode instanceof Inline) {
            System.out.println(" - \"{childNode.GetText().Trim()}\"");
        } else {
            System.out.println();
        }
    }
}

public abstract int getNodeType()

Gets the type of this node. The value of the property is NodeType integer constant.

Example:

Shows how to enumerate immediate child nodes of a composite node using NextSibling.

Document doc = new Document(getMyDir() + "Paragraphs.docx");

// Loop starting from the first child until we reach null
for (Node node = doc.getFirstSection().getBody().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 remove all nodes of a specific type from a composite node.

Document doc = new Document(getMyDir() + "Tables.docx");

Assert.assertEquals(2, doc.getChildNodes(NodeType.TABLE, true).getCount());

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

while (curNode != null) {
    // Save the next sibling node as a variable in case we want to move to it after deleting this node
    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;
}

Assert.assertEquals(0, doc.getChildNodes(NodeType.TABLE, true).getCount());

Example:

Shows how to efficiently visit all direct and indirect children of a composite node.

public void recurseAllNodes() throws Exception {
    Document doc = new Document(getMyDir() + "Paragraphs.docx");

    // Any node that can contain child nodes, such as the document itself, is composite
    Assert.assertTrue(doc.isComposite());

    // Invoke the recursive function that will go through and print all the child nodes of a composite node
    traverseAllNodes(doc, 0);
}

/// <summary>
/// Recursively traverses a node tree while printing the type of each node with an indent depending on depth as well as the contents of all inline nodes.
/// </summary>
@Test(enabled = false)
public void traverseAllNodes(CompositeNode parentNode, int depth) {
    // Loop through immediate children of a node
    for (Node childNode = parentNode.getFirstChild(); childNode != null; childNode = childNode.getNextSibling()) {
        System.out.println(MessageFormat.format("{0}{1}", String.format("    ", depth), Node.nodeTypeToString(childNode.getNodeType())));

        // Recurse into the node if it is a composite node
        if (childNode.isComposite()) {
            System.out.println();
            traverseAllNodes((CompositeNode) childNode, depth + 1);
        } else if (childNode instanceof Inline) {
            System.out.println(" - \"{childNode.GetText().Trim()}\"");
        } else {
            System.out.println();
        }
    }
}

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.

Document doc = new Document();

// Get the document's first paragraph and append a child node to it in the form of a run with text
Paragraph para = doc.getFirstSection().getBody().getFirstParagraph();

// When inserting a new node, the document that the node will belong to must be provided as an argument
Run run = new Run(doc, "Hello world!");
para.appendChild(run);

// The node lineage can be traced back to the document itself
Assert.assertEquals(para, run.getParentNode());
Assert.assertEquals(doc.getFirstSection().getBody(), para.getParentNode());
Assert.assertEquals(doc.getFirstSection(), doc.getFirstSection().getBody().getParentNode());
Assert.assertEquals(doc, doc.getFirstSection().getParentNode());

Example:

Shows how to create a node and set its owning document.

// 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));

public Node getPreviousSibling()

Gets the node immediately preceding this node.

If there is no preceding node, a null is returned.

Example:

Shows how to use of methods of Node and CompositeNode to remove a section before the last section in the document.

Document doc = new Document();
DocumentBuilder builder = new DocumentBuilder(doc);

// Create a second section by inserting a section break and add text to both sections
builder.writeln("Section 1 text.");
builder.insertBreak(BreakType.SECTION_BREAK_CONTINUOUS);
builder.writeln("Section 2 text.");

// Both sections are siblings of each other
Section lastSection = (Section) doc.getLastChild();
Section firstSection = (Section) lastSection.getPreviousSibling();

// Remove a section based on its sibling relationship with another section
if (lastSection.getPreviousSibling() != null)
    doc.removeChild(firstSection);

// The section we removed was the first one, leaving the document with only the second
Assert.assertEquals("Section 2 text.", doc.getText().trim());

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.

// Insert two sections into a blank document
Document doc = new Document();
DocumentBuilder builder = new DocumentBuilder(doc);

builder.write("Section 1. ");
builder.insertBreak(BreakType.SECTION_BREAK_CONTINUOUS);
builder.write("Section 2.");

// Verify the whole text of the document
Assert.assertEquals("Section 1. \fSection 2.", doc.getText().trim());

// 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
Assert.assertEquals("Section 2.", doc.getText().trim());

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

Accepts a visitor.

Enumerates over this node and all of its children. Each node calls a corresponding method on DocumentVisitor.

For more info see the Visitor design pattern.

Parameters:

visitor - The visitor that will visit the nodes.

Returns:

True if all nodes were visited; false if DocumentVisitor stopped the operation before visiting all nodes.

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() + "Hidden content.docx");

    // 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.RemoveHiddenContentFromDocument.docx");
}

/**
 * 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 (fieldStart.getFont().getHidden()) {
            fieldStart.remove();
        }

        return VisitorAction.CONTINUE;
    }

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

        return VisitorAction.CONTINUE;
    }

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

        return VisitorAction.CONTINUE;
    }

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

        return VisitorAction.CONTINUE;
    }

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

        return VisitorAction.CONTINUE;
    }

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

        return VisitorAction.CONTINUE;
    }

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

        return VisitorAction.CONTINUE;
    }

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

        return VisitorAction.CONTINUE;
    }

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

        return VisitorAction.CONTINUE;
    }

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

        return VisitorAction.CONTINUE;
    }

    /// <summary>
    /// Called when a SpecialCharacter is encountered in the document.
    /// </summary>
    public /*override*/ /*VisitorAction*/int visitSpecialChar(SpecialChar specialChar) {
        if (specialChar.getFont().getHidden())
            specialChar.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 algorithm,
        // 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;
    }

public Node deepClone(boolean isCloneChildren)

Creates a duplicate of the node.

This method serves as a copy constructor for nodes. The cloned node has no parent, but belongs to the same document as the original node.

This method always performs a deep copy of the node. The isCloneChildren parameter specifies whether to perform copy all child nodes as well.

Parameters:

isCloneChildren - True to recursively clone the subtree under the specified node; false to clone only the node itself.

Returns:

The cloned node.

Example:

Shows how to clone composite nodes with and without their child nodes.

Document doc = new Document();
Paragraph para = doc.getFirstSection().getBody().getFirstParagraph();
para.appendChild(new Run(doc, "Hello world!"));

// Clone the paragraph and the child nodes
Node cloneWithChildren = para.deepClone(true);

Assert.assertTrue(((CompositeNode) cloneWithChildren).hasChildNodes());
Assert.assertEquals("Hello world!", cloneWithChildren.getText().trim());

// Clone the paragraph without its clild nodes
Node cloneWithoutChildren = para.deepClone(false);

Assert.assertFalse(((CompositeNode) cloneWithoutChildren).hasChildNodes());
Assert.assertEquals("", cloneWithoutChildren.getText().trim());

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() + "Nested tables.docx");
    NodeCollection tables = doc.getChildNodes(NodeType.TABLE, true);

    for (int i = 0; i < tables.getCount(); i++) {
        // First lets find if any cells in the table have tables themselves as children
        int count = getChildTableCount((Table) tables.get(i));
        System.out.println(MessageFormat.format("Table #{0} has {1} tables directly within its cells", i, 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) tables.get(i));

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

/**
 * 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;
}

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() + "Nested tables.docx");
    NodeCollection tables = doc.getChildNodes(NodeType.TABLE, true);

    for (int i = 0; i < tables.getCount(); i++) {
        // First lets find if any cells in the table have tables themselves as children
        int count = getChildTableCount((Table) tables.get(i));
        System.out.println(MessageFormat.format("Table #{0} has {1} tables directly within its cells", i, 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) tables.get(i));

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

/**
 * 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;
}

public java.lang.String getText()

Gets the text of this node and of all its children.

The returned string includes all control and special characters as described in ControlChar.

Example:

Shows how to construct an Aspose Words document node by node.

Document doc = new Document();

// A newly created blank document still comes one section, one body and one paragraph
// Calling this method will remove all those nodes to completely empty the document
doc.removeAllChildren();

// This document now has no composite nodes that content can be added to
// If we wish to edit it, we will need to repopulate its node collection,
// which we will start to do with by creating a new Section node
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);

// A section needs a body, which will contain all other nodes that can be edited
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);

// Now we can begin adding content to the document
Run run = new Run(doc);
run.setText("Hello World!");
run.getFont().setColor(Color.RED);
para.appendChild(run);

Assert.assertEquals("Hello World!" + ControlChar.SECTION_BREAK_CHAR, doc.getText());

doc.save(getArtifactsDir() + "Section.CreateFromScratch.docx");

Example:

Shows how to use control characters.

Document doc = new Document();
DocumentBuilder builder = new DocumentBuilder(doc);

// Insert paragraphs with text with DocumentBuilder.
builder.writeln("Hello world!");
builder.writeln("Hello again!");

// Converting the document to text form reveals that control characters
// represent some of the document's structural elements, such as page breaks.
Assert.assertEquals(MessageFormat.format("Hello world!{0}", ControlChar.CR) +
                MessageFormat.format("Hello again!{0}", ControlChar.CR) +
                ControlChar.PAGE_BREAK, doc.getText());

// When converting a document to string form,
// we can omit some of the control characters with the Trim method.
Assert.assertEquals(MessageFormat.format("Hello world!{0}", ControlChar.CR) +
                "Hello again!", doc.getText().trim());

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.

Document doc = new Document(getMyDir() + "Images.docx");
Assert.assertEquals(doc.getChildNodes(NodeType.SHAPE, true).getCount(), 10);

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;
}

// The only remaining shape doesn't have an image
Assert.assertEquals(1, doc.getChildNodes(NodeType.SHAPE, true).getCount());
Assert.assertFalse(((Shape) doc.getChild(NodeType.SHAPE, 0, true)).hasImage());

public static java.lang.String nodeTypeToString(int nodeType)

A utility method that converts a node type enum value into a user friendly string.

Parameters:

nodeType - A NodeType value.

Example:

Shows how to efficiently visit all direct and indirect children of a composite node.

public void recurseAllNodes() throws Exception {
    Document doc = new Document(getMyDir() + "Paragraphs.docx");

    // Any node that can contain child nodes, such as the document itself, is composite
    Assert.assertTrue(doc.isComposite());

    // Invoke the recursive function that will go through and print all the child nodes of a composite node
    traverseAllNodes(doc, 0);
}

/// <summary>
/// Recursively traverses a node tree while printing the type of each node with an indent depending on depth as well as the contents of all inline nodes.
/// </summary>
@Test(enabled = false)
public void traverseAllNodes(CompositeNode parentNode, int depth) {
    // Loop through immediate children of a node
    for (Node childNode = parentNode.getFirstChild(); childNode != null; childNode = childNode.getNextSibling()) {
        System.out.println(MessageFormat.format("{0}{1}", String.format("    ", depth), Node.nodeTypeToString(childNode.getNodeType())));

        // Recurse into the node if it is a composite node
        if (childNode.isComposite()) {
            System.out.println();
            traverseAllNodes((CompositeNode) childNode, depth + 1);
        } else if (childNode instanceof Inline) {
            System.out.println(" - \"{childNode.GetText().Trim()}\"");
        } else {
            System.out.println();
        }
    }
}

Example:

Shows how to enumerate immediate child nodes of a composite node using NextSibling.

Document doc = new Document(getMyDir() + "Paragraphs.docx");

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

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.

Document doc = new Document(getMyDir() + "Images.docx");
Assert.assertEquals(doc.getChildNodes(NodeType.SHAPE, true).getCount(), 10);

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;
}

// The only remaining shape doesn't have an image
Assert.assertEquals(1, doc.getChildNodes(NodeType.SHAPE, true).getCount());
Assert.assertFalse(((Shape) doc.getChild(NodeType.SHAPE, 0, true)).hasImage());

public void remove()

Removes itself from the parent.

Example:

Shows how to delete all images from a document.

Document doc = new Document(getMyDir() + "Images.docx");
Assert.assertEquals(doc.getChildNodes(NodeType.SHAPE, true).getCount(), 10);

// 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();

// The only remaining shape doesn't have an image
Assert.assertEquals(1, doc.getChildNodes(NodeType.SHAPE, true).getCount());
Assert.assertFalse(((Shape) doc.getChild(NodeType.SHAPE, 0, true)).hasImage());

Example:

Shows how to remove all nodes of a specific type from a composite node.

Document doc = new Document(getMyDir() + "Tables.docx");

Assert.assertEquals(2, doc.getChildNodes(NodeType.TABLE, true).getCount());

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

while (curNode != null) {
    // Save the next sibling node as a variable in case we want to move to it after deleting this node
    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;
}

Assert.assertEquals(0, doc.getChildNodes(NodeType.TABLE, true).getCount());

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.

Document doc = new Document(getMyDir() + "Document.docx");

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

// When ToString is called using the html SaveFormat overload then the node is converted directly to html
Assert.assertEquals("<p style=\"margin-top:0pt; margin-bottom:8pt; line-height:108%; font-size:12pt\">" +
        "<span style=\"font-family:'Times New Roman'\">Hello World!</span>" +
        "</p>", node.toString(SaveFormat.HTML));

// We can also modify the result of this conversion using a SaveOptions object
HtmlSaveOptions saveOptions = new HtmlSaveOptions();
saveOptions.setExportRelativeFontSize(true);

Assert.assertEquals("<p style=\"margin-top:0pt; margin-bottom:8pt; line-height:108%\">" +
        "<span style=\"font-family:'Times New Roman'\">Hello World!</span>" +
        "</p>", node.toString(saveOptions));

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() + "Rendering.docx");
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("List item 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("\tNumerical Id: " + label.getLabelValue());

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

        listParaCount++;
    }
}

Example:

Exports the content of a node to String in HTML format.

Document doc = new Document(getMyDir() + "Document.docx");

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

// When ToString is called using the html SaveFormat overload then the node is converted directly to html
Assert.assertEquals("<p style=\"margin-top:0pt; margin-bottom:8pt; line-height:108%; font-size:12pt\">" +
        "<span style=\"font-family:'Times New Roman'\">Hello World!</span>" +
        "</p>", node.toString(SaveFormat.HTML));

// We can also modify the result of this conversion using a SaveOptions object
HtmlSaveOptions saveOptions = new HtmlSaveOptions();
saveOptions.setExportRelativeFontSize(true);

Assert.assertEquals("<p style=\"margin-top:0pt; margin-bottom:8pt; line-height:108%\">" +
        "<span style=\"font-family:'Times New Roman'\">Hello World!</span>" +
        "</p>", node.toString(saveOptions));

Example:

Shows the difference between calling the GetText and ToString methods on a node.

Document doc = new Document();

DocumentBuilder builder = new DocumentBuilder(doc);
builder.insertField("MERGEFIELD Field");

// GetText will retrieve the visible text as well as field codes and special characters.
Assert.assertEquals("\u0013MERGEFIELD Field\u0014«Field»\u0015\f", doc.getText());

// ToString will give us the document's appearance if saved to a passed save format.
Assert.assertEquals("«Field»\r\n", doc.toString(SaveFormat.TEXT));