com.aspose.words
Class FieldStart

java.lang.Object
  Node
      Inline
          SpecialChar
              FieldChar
                  com.aspose.words.FieldStart

All Implemented Interfaces:

java.lang.Cloneable, java.lang.Iterable

public class FieldStart 
extends FieldChar

import com.aspose.words.*;
import java.lang.Exception;
import java.text.MessageFormat;
import java.util.regex.Pattern;
import java.util.regex.Matcher;

/// <summary>
/// Shows how to replace hyperlinks in a Word document.
/// </summary>
public class ExReplaceHyperlinks extends ExBase
{
    /// <summary>
    /// Finds all hyperlinks in a Word document and changes their URL and display name.
    /// </summary>
    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 (Node fieldStartNode : fieldStarts)
        {
            FieldStart fieldStart = (FieldStart) fieldStartNode;
            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 Hyperlink class allows to set the target URL and the display name
                // of the link easily by setting the properties.
                hyperlink.setTarget(NewUrl);
                hyperlink.setName(NewName);
            }
        }

        doc.save(getMyDir() + "ReplaceHyperlinks Out.doc");
    }

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

/// <summary>
/// This "facade" class makes it easier to work with a hyperlink field in a Word document.
///
/// 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.
///
/// [FieldStart][Run - field code][FieldSeparator][Run - field result][FieldEnd]
///
/// The field code contains a string in one of these formats:
/// HYPERLINK "url"
/// HYPERLINK \l "bookmark name"
///
/// The field result contains text that is displayed to the user.
/// </summary>
class Hyperlink
{
    Hyperlink(FieldStart fieldStart) throws Exception
    {
        if (fieldStart == null)
            throw new Exception("Argument 'fieldStart' is null");
        if (fieldStart.getFieldType() != FieldType.FIELD_HYPERLINK)
            throw new Exception("Field start type must be FieldHyperlink.");

        mFieldStart = fieldStart;

        // Find the field separator node.
        mFieldSeparator = findNextSibling(mFieldStart, NodeType.FIELD_SEPARATOR);
        if (mFieldSeparator == null)
            throw new Exception("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 match = gRegex.matcher(fieldCode.trim());
        if (match.matches())
        {
            mIsLocal = match.group(1) != null;    //The link is local if \l is present in the field code.
            mTarget = match.group(2);
        }
    }

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

    public void setName(String value) throws Exception
    {
        // 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);
    }

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

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

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

    public void isLocal(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(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);
    }

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

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

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

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

    /// <summary>
    /// RK I am notoriously bad at regexes. It seems I don't understand their way of thinking.
    /// </summary>
    private static Pattern gRegex = 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
        );
}

public int getNodeType()

Returns NodeType.FIELD_START. The value of the property is NodeType integer constant.

public int getFieldType()

Returns the type of the field. The value of the property is FieldType integer constant.

public Paragraph getParentParagraph()

Retrieves the parent Paragraph of this node.

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 pararagraph 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 \u000c is automatically appended. \u000c is the end of section character.
Assert.assertEquals("Hello World!\u000c", doc.getText());

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

public boolean isInsertRevision()

Returns true if this object was inserted in Microsoft Word while change tracking was enabled.

public boolean isDeleteRevision()

Returns true if this object was deleted in Microsoft Word while change tracking was enabled.

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.
Assert.assertEquals(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.
Assert.assertNull(para.getParentNode());

// But the paragraph node knows its document.
Assert.assertEquals(doc, para.getDocument());

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

// The paragraph node is now a child of the Body node.
Assert.assertNotNull(para.getParentNode());

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 yed 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.
Assert.assertNull(para.getParentNode());

// But the paragraph node knows its document.
Assert.assertEquals(doc, para.getDocument());

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

// The paragraph node is now a child of the Body node.
Assert.assertNotNull(para.getParentNode());

public Node getPreviousSibling()

Gets the node immediately preceding this node.

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

Note: Calculating the value of this property iterates from the first child node of ParenNode to this node.

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);

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.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);
}

/// <summary>
/// A simple function that will walk through all children of a specified node recursively
/// and print the type of each node to the screen.
/// </summary>
private void traverseAllNodes(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(childNode.getNodeType());

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

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);
}

/// <summary>
/// A simple function that will walk through all children of a specified node recursively
/// and print the type of each node to the screen.
/// </summary>
private void traverseAllNodes(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(childNode.getNodeType());

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

public Range getRange()

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

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.

public java.lang.String getText()

Gets the special character that this node represents.

Returns:

The string that contains the character that this node represents.

public Node deepClone(boolean isCloneChildren)
              throws java.lang.Exception

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.

public Node 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.

public Node 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.

public void remove()
           throws java.lang.Exception

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;
}

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.canHaveImage())
            shape.remove();
    }

    curNode = nextNode;
}

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.

public java.lang.String toTxt()
            throws java.lang.Exception

Exports the content of the node into a string in plain text format.

This method removes field codes and Microsoft Word control characters, uses CrLf (or any other) combination of characters to mark ends of paragraphs in the resulting string. It produces a different result from getText() which just gets the text from the node without removing field codes or special characters.

Returns:

The content of the node in plain text format.

See Also:

SaveOptions.TxtExportParagraphBreak, SaveOptions.TxtExportHeadersFooters

public java.lang.Object getDirectRunAttr(int fontAttr)

Reserved for internal use.

public int getDirectRunAttrsCount()

Reserved for internal use.

public void getDirectRunAttrByIndex(int index, int[] key, java.lang.Object[] value)

Reserved for internal use.

public java.lang.Object fetchInheritedRunAttr(int fontAttr)
                            throws java.lang.Exception

Reserved for internal use.

public void setRunAttr(int fontAttr, java.lang.Object value)

Reserved for internal use.

public void clearRunAttrs()

Reserved for internal use.

public Aspose.Words.RunPr getSrcRunPr()

Reserved for internal use.

public Aspose.Words.RunPr getRunPr()

Reserved for internal use.

public Paragraph getParentParagraph()

Reserved for internal use.

public DocumentBase getDocument()

Reserved for internal use.

public java.util.Iterator iterator()

Provides support for the for each style iteration over child nodes of the node.

Non-composite nodes (such as Run, SpecialChar etc) return an empty iterator used internally for XPath traversal.