com.aspose.words

com.aspose.words

Class FieldStart

  • All Implemented Interfaces:
    java.lang.Cloneable
    public class FieldStart 
    extends FieldChar

Represents a start of a Word field in a document.

FieldStart is an inline-level node and represented by the ControlChar.FIELD_START_CHAR control character in the document.

FieldStart can only be a child of Paragraph.

A complete field in a Microsoft Word document is a complex structure consisting of a field start character, field code, field separator character, field result and field end character. Some fields only have field start, field code and field end.

To easily insert a new field into a document, use the DocumentBuilder.insertField(java.lang.String) method.

Example:

Shows how to work with a document's field collection.
public void fieldCollection() throws Exception {
    // Open a document that has fields
    Document doc = new Document(getMyDir() + "Document.ContainsFields.docx");

    // Get the collection that contains all the fields in a document
    FieldCollection fields = doc.getRange().getFields();
    Assert.assertEquals(fields.getCount(), 6);

    // Iterate over the field collection and print contents and type of every field using a custom visitor implementation
    FieldVisitor fieldVisitor = new FieldVisitor();

    Iterator<Field> fieldEnumerator = fields.iterator();

    while (fieldEnumerator.hasNext()) {
        if (fieldEnumerator.next() != null) {
            Field currentField = fieldEnumerator.next();

            currentField.getStart().accept(fieldVisitor);
            if (currentField.getSeparator() != null) {
                currentField.getSeparator().accept(fieldVisitor);
            }
            currentField.getEnd().accept(fieldVisitor);
        } else {
            System.out.println("There are no fields in the document.");
        }
    }

    System.out.println(fieldVisitor.getText());

    // Get a field to remove itself
    fields.get(0).remove();
    Assert.assertEquals(fields.getCount(), 5);

    // Remove a field by reference
    Field lastField = fields.get(3);
    fields.remove(lastField);
    Assert.assertEquals(fields.getCount(), 4);

    // Remove a field by index
    fields.removeAt(2);
    Assert.assertEquals(fields.getCount(), 3);

    // Remove all fields from the document
    fields.clear();
    Assert.assertEquals(fields.getCount(), 0);
}

/// <summary>
/// Document visitor implementation that prints field info
/// </summary>
public static class FieldVisitor extends DocumentVisitor {
    public FieldVisitor() {
        mBuilder = new StringBuilder();
    }

    /// <summary>
    /// Gets the plain text of the document that was accumulated by the visitor.
    /// </summary>
    public String getText() {
        return mBuilder.toString();
    }

    /// <summary>
    /// Called when a FieldStart node is encountered in the document.
    /// </summary>
    public int visitFieldStart(final FieldStart fieldStart) {
        mBuilder.append("Found field: " + fieldStart.getFieldType() + "\r\n");
        mBuilder.append("\tField code: " + fieldStart.getField().getFieldCode() + "\r\n");
        mBuilder.append("\tDisplayed as: " + fieldStart.getField().getResult() + "\r\n");

        return VisitorAction.CONTINUE;
    }

    /// <summary>
    /// Called when a FieldSeparator node is encountered in the document.
    /// </summary>
    public int visitFieldSeparator(final FieldSeparator fieldSeparator) {
        mBuilder.append("\tFound separator: " + fieldSeparator.getText() + "\r\n");

        return VisitorAction.CONTINUE;
    }

    /// <summary>
    /// Called when a FieldEnd node is encountered in the document.
    /// </summary>
    public int visitFieldEnd(final FieldEnd fieldEnd) {
        mBuilder.append("End of field: " + fieldEnd.getFieldType() + "\r\n");

        return VisitorAction.CONTINUE;
    }

    private StringBuilder mBuilder;
}

Example:

Finds all hyperlinks in a Word document and changes their URL and display name.
import com.aspose.words.*;
import org.testng.annotations.Test;

import java.util.regex.Matcher;
import java.util.regex.Pattern;

/**
 * Shows how to replace hyperlinks in a Word document.
 */
public class ExReplaceHyperlinks extends ApiExampleBase {
    /**
     * Finds all hyperlinks in a Word document and changes their URL and display name.
     */
    public void replaceHyperlinks() throws Exception {
        // Specify your document name here.
        Document doc = new Document(getMyDir() + "ReplaceHyperlinks.doc");

        // Hyperlinks in a Word documents are fields, select all field start nodes so we can find the hyperlinks.
        NodeList fieldStarts = doc.selectNodes("//FieldStart");
        for (FieldStart fieldStart : (Iterable<FieldStart>) fieldStarts) {
            if (fieldStart.getFieldType() == FieldType.FIELD_HYPERLINK) {
                // The field is a hyperlink field, use the "facade" class to help to deal with the field.
                Hyperlink hyperlink = new Hyperlink(fieldStart);

                // Some hyperlinks can be local (links to bookmarks inside the document), ignore these.
                if (hyperlink.isLocal()) continue;

                // The ApiExamples.Tests.Examples.Hyperlink class allows to set the target URL and the display name
                // of the link easily by setting the properties.
                hyperlink.setTarget(NEW_URL);
                hyperlink.setName(NEW_NAME);
            }
        }

        doc.save(getArtifactsDir() + "ReplaceHyperlinks.doc");
    }

    private static final String NEW_URL = "http://www.aspose.com";
    private static final String NEW_NAME = "Aspose - The .NET & Java Component Publisher";
}


/**
 * This "facade" class makes it easier to work with a hyperlink field in a Word document.
 * <p>
 * A hyperlink is represented by a HYPERLINK field in a Word document. A field in Aspose.Words
 * consists of several nodes and it might be difficult to work with all those nodes directly.
 * Note this is a simple implementation and will work only if the hyperlink code and name
 * each consist of one Run only.
 * <p>
 * [FieldStart][Run - field code][FieldSeparator][Run - field result][FieldEnd]
 * <p>
 * The field code contains a String in one of these formats:
 * HYPERLINK "url"
 * HYPERLINK \l "bookmark name"
 * <p>
 * The field result contains text that is displayed to the user.
 */
class Hyperlink {
    Hyperlink(final FieldStart fieldStart) throws Exception {
        if (fieldStart == null) {
            throw new IllegalArgumentException("fieldStart");
        }

        if (fieldStart.getFieldType() != FieldType.FIELD_HYPERLINK) {
            throw new IllegalArgumentException("Field start type must be FieldHyperlink.");
        }

        mFieldStart = fieldStart;

        // Find the field separator node.
        mFieldSeparator = findNextSibling(mFieldStart, NodeType.FIELD_SEPARATOR);
        if (mFieldSeparator == null) {
            throw new IllegalStateException("Cannot find field separator.");
        }

        // Find the field end node. Normally field end will always be found, but in the example document
        // there happens to be a paragraph break included in the hyperlink and this puts the field end
        // in the next paragraph. It will be much more complicated to handle fields which span several
        // paragraphs correctly, but in this case allowing field end to be null is enough for our purposes.
        mFieldEnd = findNextSibling(mFieldSeparator, NodeType.FIELD_END);

        // Field code looks something like [ HYPERLINK "http:\\www.myurl.com" ], but it can consist of several runs.
        String fieldCode = getTextSameParent(mFieldStart.getNextSibling(), mFieldSeparator);
        Matcher matcher = G_REGEX.matcher(fieldCode.trim());
        matcher.find();
        mIsLocal = (matcher.group(1) != null) && (matcher.group(1).length() > 0);    //The link is local if \l is present in the field code.
        mTarget = matcher.group(2).toString();
    }

    /**
     * Gets or sets the display name of the hyperlink.
     */
    String getName() throws Exception {
        return getTextSameParent(mFieldSeparator, mFieldEnd);
    }

    void setName(final String value) throws Exception {
        // ApiExamples.Tests.Examples.Hyperlink display name is stored in the field result which is a Run
        // node between field separator and field end.
        Run fieldResult = (Run) mFieldSeparator.getNextSibling();
        fieldResult.setText(value);

        // But sometimes the field result can consist of more than one run, delete these runs.
        removeSameParent(fieldResult.getNextSibling(), mFieldEnd);
    }

    /**
     * Gets or sets the target url or bookmark name of the hyperlink.
     */
    String getTarget() {
        return mTarget;
    }

    void setTarget(final String value) throws Exception {
        mTarget = value;
        updateFieldCode();
    }

    /**
     * True if the hyperlink's target is a bookmark inside the document. False if the hyperlink is a url.
     */
    boolean isLocal() {
        return mIsLocal;
    }

    void isLocal(final boolean value) throws Exception {
        mIsLocal = value;
        updateFieldCode();
    }

    private void updateFieldCode() throws Exception {
        // Field code is stored in a Run node between field start and field separator.
        Run fieldCode = (Run) mFieldStart.getNextSibling();
        fieldCode.setText(java.text.MessageFormat.format("HYPERLINK {0}\"{1}\"", ((mIsLocal) ? "\\l " : ""), mTarget));

        // But sometimes the field code can consist of more than one run, delete these runs.
        removeSameParent(fieldCode.getNextSibling(), mFieldSeparator);
    }

    /**
     * Goes through siblings starting from the start node until it finds a node of the specified type or null.
     */
    private static Node findNextSibling(final Node startNode, final int nodeType) {
        for (Node node = startNode; node != null; node = node.getNextSibling()) {
            if (node.getNodeType() == nodeType) return node;
        }
        return null;
    }

    /**
     * Retrieves text from start up to but not including the end node.
     */
    private static String getTextSameParent(final Node startNode, final Node endNode) {
        if ((endNode != null) && (startNode.getParentNode() != endNode.getParentNode())) {
            throw new IllegalArgumentException("Start and end nodes are expected to have the same parent.");
        }

        StringBuilder builder = new StringBuilder();
        for (Node child = startNode; !child.equals(endNode); child = child.getNextSibling()) {
            builder.append(child.getText());
        }

        return builder.toString();
    }

    /**
     * Removes nodes from start up to but not including the end node.
     * Start and end are assumed to have the same parent.
     */
    private static void removeSameParent(final Node startNode, final Node endNode) {
        if ((endNode != null) && (startNode.getParentNode() != endNode.getParentNode())) {
            throw new IllegalArgumentException("Start and end nodes are expected to have the same parent.");
        }

        Node curChild = startNode;
        while ((curChild != null) && (curChild != endNode)) {
            Node nextChild = curChild.getNextSibling();
            curChild.remove();
            curChild = nextChild;
        }
    }

    private final Node mFieldStart;
    private final Node mFieldSeparator;
    private final Node mFieldEnd;
    private boolean mIsLocal;
    private String mTarget;

    /**
     * RK I am notoriously bad at regexes. It seems I don't understand their way of thinking.
     */
    private static final Pattern G_REGEX = Pattern.compile("\\S+" +            // one or more non spaces HYPERLINK or other word in other languages
            "\\s+" +            // one or more spaces
            "(?:\"\"\\s+)?" +    // non capturing optional "" and one or more spaces, found in one of the customers files.
            "(\\\\l\\s+)?" +    // optional \l flag followed by one or more spaces
            "\"" +                // one apostrophe
            "([^\"]+)" +        // one or more chars except apostrophe (hyperlink target)
            "\""                // one closing apostrophe
    );
}

Property Getters/Setters Summary
DocumentBasegetDocument()
Gets the document to which this node belongs.
intgetFieldType()
Returns the type of the field. The value of the property is FieldType integer constant.
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.
booleanisDirty()
void
isDirty(booleanvalue)
           Gets or sets whether the current result of the field is no longer correct (stale) due to other modifications made to the document.
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.
booleanisLocked()
void
isLocked(booleanvalue)
           Gets or sets whether the parent field is locked (should not recalculate its result).
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.FIELD_START. 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.
FieldgetField()
Returns a field for the field char.
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));

      • getFieldType

        public int getFieldType()
        Returns the type of the field. The value of the property is FieldType integer constant.

        Example:

        Demonstrates how to retrieve the field class from an existing FieldStart node in the document.
        Document doc = new Document(getMyDir() + "Document.TableOfContents.doc");

FieldChar fieldStart = (FieldChar) doc.getChild(NodeType.FIELD_START, 0, true);
Assert.assertEquals(fieldStart.getFieldType(), FieldType.FIELD_TOC);
Assert.assertEquals(fieldStart.isDirty(), true);
Assert.assertEquals(fieldStart.isLocked(), false);

// Retrieve the facade object which represents the field in the document.
Field field = fieldStart.getField();

Assert.assertEquals(false, field.isLocked());
Assert.assertEquals(" TOC \\o \"1-3\" \\h \\z \\u ", field.getFieldCode());

// This updates only this field in the document.
field.update();

      • 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());

      • isDirty/isDirty

        public boolean isDirty() / public void isDirty(boolean value)
        Gets or sets whether the current result of the field is no longer correct (stale) due to other modifications made to the document.

        Example:

        Demonstrates how to retrieve the field class from an existing FieldStart node in the document.
        Document doc = new Document(getMyDir() + "Document.TableOfContents.doc");

FieldChar fieldStart = (FieldChar) doc.getChild(NodeType.FIELD_START, 0, true);
Assert.assertEquals(fieldStart.getFieldType(), FieldType.FIELD_TOC);
Assert.assertEquals(fieldStart.isDirty(), true);
Assert.assertEquals(fieldStart.isLocked(), false);

// Retrieve the facade object which represents the field in the document.
Field field = fieldStart.getField();

Assert.assertEquals(false, field.isLocked());
Assert.assertEquals(" TOC \\o \"1-3\" \\h \\z \\u ", field.getFieldCode());

// This updates only this field in the document.
field.update();

      • 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());

      • isLocked/isLocked

        public boolean isLocked() / public void isLocked(boolean value)
        Gets or sets whether the parent field is locked (should not recalculate its result).

        Example:

        Demonstrates how to retrieve the field class from an existing FieldStart node in the document.
        Document doc = new Document(getMyDir() + "Document.TableOfContents.doc");

FieldChar fieldStart = (FieldChar) doc.getChild(NodeType.FIELD_START, 0, true);
Assert.assertEquals(fieldStart.getFieldType(), FieldType.FIELD_TOC);
Assert.assertEquals(fieldStart.isDirty(), true);
Assert.assertEquals(fieldStart.isLocked(), false);

// Retrieve the facade object which represents the field in the document.
Field field = fieldStart.getField();

Assert.assertEquals(false, field.isLocked());
Assert.assertEquals(" TOC \\o \"1-3\" \\h \\z \\u ", field.getFieldCode());

// This updates only this field in the document.
field.update();

      • 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.FIELD_START. 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.visitFieldStart(com.aspose.words.FieldStart).

        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.

        Example:

        Shows how to work with a document's field collection.
        public void fieldCollection() throws Exception {
    // Open a document that has fields
    Document doc = new Document(getMyDir() + "Document.ContainsFields.docx");

    // Get the collection that contains all the fields in a document
    FieldCollection fields = doc.getRange().getFields();
    Assert.assertEquals(fields.getCount(), 6);

    // Iterate over the field collection and print contents and type of every field using a custom visitor implementation
    FieldVisitor fieldVisitor = new FieldVisitor();

    Iterator<Field> fieldEnumerator = fields.iterator();

    while (fieldEnumerator.hasNext()) {
        if (fieldEnumerator.next() != null) {
            Field currentField = fieldEnumerator.next();

            currentField.getStart().accept(fieldVisitor);
            if (currentField.getSeparator() != null) {
                currentField.getSeparator().accept(fieldVisitor);
            }
            currentField.getEnd().accept(fieldVisitor);
        } else {
            System.out.println("There are no fields in the document.");
        }
    }

    System.out.println(fieldVisitor.getText());

    // Get a field to remove itself
    fields.get(0).remove();
    Assert.assertEquals(fields.getCount(), 5);

    // Remove a field by reference
    Field lastField = fields.get(3);
    fields.remove(lastField);
    Assert.assertEquals(fields.getCount(), 4);

    // Remove a field by index
    fields.removeAt(2);
    Assert.assertEquals(fields.getCount(), 3);

    // Remove all fields from the document
    fields.clear();
    Assert.assertEquals(fields.getCount(), 0);
}

/// <summary>
/// Document visitor implementation that prints field info
/// </summary>
public static class FieldVisitor extends DocumentVisitor {
    public FieldVisitor() {
        mBuilder = new StringBuilder();
    }

    /// <summary>
    /// Gets the plain text of the document that was accumulated by the visitor.
    /// </summary>
    public String getText() {
        return mBuilder.toString();
    }

    /// <summary>
    /// Called when a FieldStart node is encountered in the document.
    /// </summary>
    public int visitFieldStart(final FieldStart fieldStart) {
        mBuilder.append("Found field: " + fieldStart.getFieldType() + "\r\n");
        mBuilder.append("\tField code: " + fieldStart.getField().getFieldCode() + "\r\n");
        mBuilder.append("\tDisplayed as: " + fieldStart.getField().getResult() + "\r\n");

        return VisitorAction.CONTINUE;
    }

    /// <summary>
    /// Called when a FieldSeparator node is encountered in the document.
    /// </summary>
    public int visitFieldSeparator(final FieldSeparator fieldSeparator) {
        mBuilder.append("\tFound separator: " + fieldSeparator.getText() + "\r\n");

        return VisitorAction.CONTINUE;
    }

    /// <summary>
    /// Called when a FieldEnd node is encountered in the document.
    /// </summary>
    public int visitFieldEnd(final FieldEnd fieldEnd) {
        mBuilder.append("End of field: " + fieldEnd.getFieldType() + "\r\n");

        return VisitorAction.CONTINUE;
    }

    private StringBuilder mBuilder;
}

      • 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(type);

    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(type);
    }

    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.

      • getField

        public Field getField()
        Returns a field for the field char. A new Field object is created each time the method is called.
        Returns:
        A field for the field char.

        Example:

        Demonstrates how to retrieve the field class from an existing FieldStart node in the document.
        Document doc = new Document(getMyDir() + "Document.TableOfContents.doc");

FieldChar fieldStart = (FieldChar) doc.getChild(NodeType.FIELD_START, 0, true);
Assert.assertEquals(fieldStart.getFieldType(), FieldType.FIELD_TOC);
Assert.assertEquals(fieldStart.isDirty(), true);
Assert.assertEquals(fieldStart.isLocked(), false);

// Retrieve the facade object which represents the field in the document.
Field field = fieldStart.getField();

Assert.assertEquals(false, field.isLocked());
Assert.assertEquals(" TOC \\o \"1-3\" \\h \\z \\u ", field.getFieldCode());

// This updates only this field in the document.
field.update();

      • 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.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.

      • 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);