java.lang.ObjectNode
Inline
SpecialChar
FieldChar
com.aspose.words.FieldStart
public class FieldStart
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 Example: Example:
public void fieldCollection() throws Exception {
// Create a new document and insert some fields
Document doc = new Document();
DocumentBuilder builder = new DocumentBuilder(doc);
builder.insertField(" DATE \\@ \"dddd, d MMMM yyyy\" ");
builder.insertField(" TIME ");
builder.insertField(" REVNUM ");
builder.insertField(" AUTHOR \"John Doe\" ");
builder.insertField(" SUBJECT \"My Subject\" ");
builder.insertField(" QUOTE \"Hello world!\" ");
doc.updateFields();
// 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;
}
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 fields() throws Exception {
// Specify your document name here
Document doc = new Document(getMyDir() + "Hyperlinks.docx");
// 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 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.Fields.docx");
}
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 {
// 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 hyperlinks 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;
private static 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 | ||
---|---|---|
DocumentBase | getDocument() | → inherited from Node |
Gets the document to which this node belongs. | ||
int | getFieldType() | → inherited from FieldChar |
Returns the type of the field. The value of the property is FieldType integer constant. | ||
Font | getFont() | → inherited from Inline |
Provides access to the font formatting of this object. | ||
boolean | isComposite() | → inherited from Node |
Returns true if this node can contain other nodes. | ||
boolean | isDeleteRevision() | → inherited from Inline |
Returns true if this object was deleted in Microsoft Word while change tracking was enabled. | ||
boolean | isDirty() | → inherited from FieldChar |
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. | ||
boolean | isFormatRevision() | → inherited from Inline |
Returns true if formatting of the object was changed in Microsoft Word while change tracking was enabled. | ||
boolean | isInsertRevision() | → inherited from Inline |
Returns true if this object was inserted in Microsoft Word while change tracking was enabled. | ||
boolean | isLocked() | → inherited from FieldChar |
void | isLocked(boolean value) | |
Gets or sets whether the parent field is locked (should not recalculate its result). | ||
boolean | isMoveFromRevision() | → inherited from Inline |
Returns true if this object was moved (deleted) in Microsoft Word while change tracking was enabled. | ||
boolean | isMoveToRevision() | → inherited from Inline |
Returns true if this object was moved (inserted) in Microsoft Word while change tracking was enabled. | ||
Node | getNextSibling() | → inherited from Node |
Gets the node immediately following this node. | ||
int | getNodeType() | |
Returns |
||
CompositeNode | getParentNode() | → inherited from Node |
Gets the immediate parent of this node. | ||
Paragraph | getParentParagraph() | → inherited from Inline |
Retrieves the parent |
||
Node | getPreviousSibling() | → inherited from Node |
Gets the node immediately preceding this node. | ||
Range | getRange() | → inherited from Node |
Returns a Range object that represents the portion of a document that is contained in this node. |
Method Summary | ||
---|---|---|
boolean | accept(DocumentVisitor visitor) | |
Accepts a visitor. | ||
Node | deepClone(boolean isCloneChildren) | → inherited from Node |
CompositeNode | getAncestor(int ancestorType) | → inherited from Node |
Gets the first ancestor of the specified |
||
CompositeNode | getAncestor(java.lang.Class ancestorType) | → inherited from Node |
Gets the first ancestor of the specified object type. | ||
Field | getField() | → inherited from FieldChar |
Returns a field for the field char. | ||
java.lang.String | getText() | → inherited from SpecialChar |
Gets the special character that this node represents. | ||
Node | nextPreOrder(Node rootNode) | → inherited from Node |
Gets next node according to the pre-order tree traversal algorithm. | ||
Node | previousPreOrder(Node rootNode) | → inherited from Node |
Gets the previous node according to the pre-order tree traversal algorithm. | ||
void | remove() | → inherited from Node |
Removes itself from the parent. | ||
java.lang.String | toString(SaveOptions saveOptions) | → inherited from Node |
Exports the content of the node into a string using the specified save options. | ||
java.lang.String | toString(int saveFormat) | → inherited from Node |
Exports the content of the node into a string in the specified format. |
Property Getters/Setters Detail |
---|
getDocument | → inherited from Node |
public DocumentBase getDocument() |
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));
getFieldType | → inherited from FieldChar |
public int getFieldType() |
Example:
Demonstrates how to retrieve the field class from an existing FieldStart node in the document.Document doc = new Document(); DocumentBuilder builder = new DocumentBuilder(doc); FieldDate field = (FieldDate) builder.insertField(FieldType.FIELD_DATE, true); field.getFormat().setDateTimeFormat("dddd, MMMM dd, yyyy"); field.update(); FieldChar fieldStart = field.getStart(); Assert.assertEquals(FieldType.FIELD_DATE, fieldStart.getFieldType()); Assert.assertEquals(false, fieldStart.isDirty()); Assert.assertEquals(false, fieldStart.isLocked()); // Retrieve the facade object which represents the field in the document field = (FieldDate) fieldStart.getField(); Assert.assertEquals(false, field.isLocked()); Assert.assertEquals(" DATE \\@ \"dddd, MMMM dd, yyyy\"", field.getFieldCode()); // This updates only this field in the document field.update();
getFont | → inherited from Inline |
public Font getFont() |
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); // 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); Assert.assertEquals("Hello World!" + ControlChar.SECTION_BREAK_CHAR, doc.getText()); doc.save(getArtifactsDir() + "Section.CreateFromScratch.docx");
isComposite | → inherited from Node |
public boolean isComposite() |
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(); } } }
isDeleteRevision | → inherited from Inline |
public boolean isDeleteRevision() |
Example:
Shows how to view revision-related properties of Inline nodes.Document doc = new Document(getMyDir() + "Revision runs.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 | → inherited from FieldChar |
public boolean isDirty() / public void isDirty(boolean value) |
Example:
Demonstrates how to retrieve the field class from an existing FieldStart node in the document.Document doc = new Document(); DocumentBuilder builder = new DocumentBuilder(doc); FieldDate field = (FieldDate) builder.insertField(FieldType.FIELD_DATE, true); field.getFormat().setDateTimeFormat("dddd, MMMM dd, yyyy"); field.update(); FieldChar fieldStart = field.getStart(); Assert.assertEquals(FieldType.FIELD_DATE, fieldStart.getFieldType()); Assert.assertEquals(false, fieldStart.isDirty()); Assert.assertEquals(false, fieldStart.isLocked()); // Retrieve the facade object which represents the field in the document field = (FieldDate) fieldStart.getField(); Assert.assertEquals(false, field.isLocked()); Assert.assertEquals(" DATE \\@ \"dddd, MMMM dd, yyyy\"", field.getFieldCode()); // This updates only this field in the document field.update();
isFormatRevision | → inherited from Inline |
public boolean isFormatRevision() |
Example:
Shows how to view revision-related properties of Inline nodes.Document doc = new Document(getMyDir() + "Revision runs.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 | → inherited from Inline |
public boolean isInsertRevision() |
Example:
Shows how to view revision-related properties of Inline nodes.Document doc = new Document(getMyDir() + "Revision runs.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 | → inherited from FieldChar |
public boolean isLocked() / public void isLocked(boolean value) |
Example:
Demonstrates how to retrieve the field class from an existing FieldStart node in the document.Document doc = new Document(); DocumentBuilder builder = new DocumentBuilder(doc); FieldDate field = (FieldDate) builder.insertField(FieldType.FIELD_DATE, true); field.getFormat().setDateTimeFormat("dddd, MMMM dd, yyyy"); field.update(); FieldChar fieldStart = field.getStart(); Assert.assertEquals(FieldType.FIELD_DATE, fieldStart.getFieldType()); Assert.assertEquals(false, fieldStart.isDirty()); Assert.assertEquals(false, fieldStart.isLocked()); // Retrieve the facade object which represents the field in the document field = (FieldDate) fieldStart.getField(); Assert.assertEquals(false, field.isLocked()); Assert.assertEquals(" DATE \\@ \"dddd, MMMM dd, yyyy\"", field.getFieldCode()); // This updates only this field in the document field.update();
isMoveFromRevision | → inherited from Inline |
public boolean isMoveFromRevision() |
Example:
Shows how to view revision-related properties of Inline nodes.Document doc = new Document(getMyDir() + "Revision runs.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 | → inherited from Inline |
public boolean isMoveToRevision() |
Example:
Shows how to view revision-related properties of Inline nodes.Document doc = new Document(getMyDir() + "Revision runs.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 | → inherited from Node |
public Node getNextSibling() |
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(); } } }
getNodeType | |
public int 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(); } } }
getParentNode | → inherited from Node |
public CompositeNode getParentNode() |
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));
getParentParagraph | → inherited from Inline |
public Paragraph getParentParagraph() |
Example:
Shows how to view revision-related properties of Inline nodes.Document doc = new Document(getMyDir() + "Revision runs.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 | → inherited from Node |
public Node getPreviousSibling() |
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());
getRange | → inherited from Node |
public Range getRange() |
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());
Method Detail |
---|
accept | |
public boolean accept(DocumentVisitor visitor) throws java.lang.Exception |
Calls
For more info see the Visitor design pattern.
visitor
- The visitor that will visit the node.Example:
Shows how to work with a document's field collection.public void fieldCollection() throws Exception { // Create a new document and insert some fields Document doc = new Document(); DocumentBuilder builder = new DocumentBuilder(doc); builder.insertField(" DATE \\@ \"dddd, d MMMM yyyy\" "); builder.insertField(" TIME "); builder.insertField(" REVNUM "); builder.insertField(" AUTHOR \"John Doe\" "); builder.insertField(" SUBJECT \"My Subject\" "); builder.insertField(" QUOTE \"Hello world!\" "); doc.updateFields(); // 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 | → inherited from Node |
public Node deepClone(boolean isCloneChildren) |
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());
getAncestor | → inherited from Node |
public CompositeNode getAncestor(int ancestorType) |
ancestorType
- A 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; }
getAncestor | → inherited from Node |
public CompositeNode getAncestor(java.lang.Class ancestorType) |
The ancestor type matches if it is equal to ancestorType or derived from ancestorType.
ancestorType
- The object type of the ancestor to retrieve.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; }
getField | → inherited from FieldChar |
public Field getField() |
Example:
Demonstrates how to retrieve the field class from an existing FieldStart node in the document.Document doc = new Document(); DocumentBuilder builder = new DocumentBuilder(doc); FieldDate field = (FieldDate) builder.insertField(FieldType.FIELD_DATE, true); field.getFormat().setDateTimeFormat("dddd, MMMM dd, yyyy"); field.update(); FieldChar fieldStart = field.getStart(); Assert.assertEquals(FieldType.FIELD_DATE, fieldStart.getFieldType()); Assert.assertEquals(false, fieldStart.isDirty()); Assert.assertEquals(false, fieldStart.isLocked()); // Retrieve the facade object which represents the field in the document field = (FieldDate) fieldStart.getField(); Assert.assertEquals(false, field.isLocked()); Assert.assertEquals(" DATE \\@ \"dddd, MMMM dd, yyyy\"", field.getFieldCode()); // This updates only this field in the document field.update();
getText | → inherited from SpecialChar |
public java.lang.String getText() |
nextPreOrder | → inherited from Node |
public Node nextPreOrder(Node rootNode) |
rootNode
- The top node (limit) of traversal.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());
previousPreOrder | → inherited from Node |
public Node previousPreOrder(Node rootNode) |
rootNode
- The top node (limit) of traversal.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());
remove | → inherited from Node |
public void remove() |
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());
toString | → inherited from Node |
public java.lang.String toString(SaveOptions saveOptions) throws java.lang.Exception |
saveOptions
- Specifies the options that control how the node is saved.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));
toString | → inherited from Node |
public java.lang.String toString(int saveFormat) throws java.lang.Exception |
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(); // Enter a field into the document DocumentBuilder builder = new DocumentBuilder(doc); builder.insertField("MERGEFIELD Field"); // GetText will retrieve all field codes and special characters Assert.assertEquals("\u0013MERGEFIELD Field\u0014«Field»\u0015\f", doc.getText()); // ToString will give us the plaintext version of the document in the save format we put into the parameter Assert.assertEquals("«Field»\r\n", doc.toString(SaveFormat.TEXT));