java.lang.ObjectNode
CompositeNode
DocumentBase
com.aspose.words.GlossaryDocument
public class GlossaryDocument
Some documents, usually templates, can contain AutoText, AutoCorrect entries
and/or Building Blocks (also known as glossary document entries, document parts
or building blocks). To access building blocks, you need to load a document into a Corresponds to the glossaryDocument and docParts elements in OOXML. Example:
public void glossaryDocument() throws Exception {
Document doc = new Document();
GlossaryDocument glossaryDoc = new GlossaryDocument();
glossaryDoc.appendChild(createNewBuildingBlock(glossaryDoc, "Block 1"));
glossaryDoc.appendChild(createNewBuildingBlock(glossaryDoc, "Block 2"));
glossaryDoc.appendChild(createNewBuildingBlock(glossaryDoc, "Block 3"));
glossaryDoc.appendChild(createNewBuildingBlock(glossaryDoc, "Block 4"));
glossaryDoc.appendChild(createNewBuildingBlock(glossaryDoc, "Block 5"));
Assert.assertEquals(glossaryDoc.getBuildingBlocks().getCount(), 5);
doc.setGlossaryDocument(glossaryDoc);
// There is a different ways how to get created building blocks
Assert.assertEquals("Block 1", glossaryDoc.getFirstBuildingBlock().getName());
Assert.assertEquals("Block 2", glossaryDoc.getBuildingBlocks().get(1).getName());
Assert.assertEquals("Block 3", glossaryDoc.getBuildingBlocks().toArray()[2].getName());
Assert.assertEquals("Block 4", glossaryDoc.getBuildingBlock(BuildingBlockGallery.ALL, "(Empty Category)", "Block 4").getName());
Assert.assertEquals("Block 5", glossaryDoc.getLastBuildingBlock().getName());
// We will do that using a custom visitor, which also will give every BuildingBlock in the GlossaryDocument a unique GUID
GlossaryDocVisitor visitor = new GlossaryDocVisitor();
glossaryDoc.accept(visitor);
System.out.println(visitor.getText());
// We can find our new blocks in Microsoft Word via Insert > Quick Parts > Building Blocks Organizer...
doc.save(getArtifactsDir() + "BuildingBlocks.GlossaryDocument.dotx");
}
public static BuildingBlock createNewBuildingBlock(final GlossaryDocument glossaryDoc, final String buildingBlockName) {
BuildingBlock buildingBlock = new BuildingBlock(glossaryDoc);
buildingBlock.setName(buildingBlockName);
return buildingBlock;
}
/// <summary>
/// Simple implementation of giving each building block in a glossary document a unique GUID. Implemented as a Visitor.
/// </summary>
public static class GlossaryDocVisitor extends DocumentVisitor {
public GlossaryDocVisitor() {
mBlocksByGuid = new HashMap<>();
mBuilder = new StringBuilder();
}
public String getText() {
return mBuilder.toString();
}
public HashMap<UUID, BuildingBlock> getDictionary() {
return mBlocksByGuid;
}
public int visitGlossaryDocumentStart(final GlossaryDocument glossary) {
mBuilder.append("Glossary document found!\n");
return VisitorAction.CONTINUE;
}
public int visitGlossaryDocumentEnd(final GlossaryDocument glossary) {
mBuilder.append("Reached end of glossary!\n");
mBuilder.append("BuildingBlocks found: " + mBlocksByGuid.size() + "\r\n");
return VisitorAction.CONTINUE;
}
public int visitBuildingBlockStart(final BuildingBlock block) {
block.setGuid(UUID.randomUUID());
mBlocksByGuid.put(block.getGuid(), block);
return VisitorAction.CONTINUE;
}
public int visitBuildingBlockEnd(final BuildingBlock block) {
mBuilder.append("\tVisited block \"" + block.getName() + "\"" + "\r\n");
mBuilder.append("\t Type: " + block.getType() + "\r\n");
mBuilder.append("\t Gallery: " + block.getGallery() + "\r\n");
mBuilder.append("\t Behavior: " + block.getBehavior() + "\r\n");
mBuilder.append("\t Description: " + block.getDescription() + "\r\n");
return VisitorAction.CONTINUE;
}
private HashMap<UUID, BuildingBlock> mBlocksByGuid;
private StringBuilder mBuilder;
}
Constructor Summary |
---|
GlossaryDocument()
|
Property Getters/Setters Summary | ||
---|---|---|
Shape | getBackgroundShape() | → inherited from DocumentBase |
void | setBackgroundShape(Shape value) | |
Gets or sets the background shape of the document. Can be null. | ||
BuildingBlockCollection | getBuildingBlocks() | |
Returns a typed collection that represents all building blocks in the glossary document. | ||
NodeCollection | getChildNodes() | → inherited from CompositeNode |
Gets all immediate child nodes of this node. | ||
int | getCount() | → inherited from CompositeNode |
Gets the number of immediate children of this node. | ||
DocumentBase | getDocument() | → inherited from DocumentBase |
BuildingBlock | getFirstBuildingBlock() | |
Gets the first building block in the glossary document. | ||
Node | getFirstChild() | → inherited from CompositeNode |
Gets the first child of the node. | ||
FontInfoCollection | getFontInfos() | → inherited from DocumentBase |
Provides access to properties of fonts used in this document. | ||
boolean | hasChildNodes() | → inherited from CompositeNode |
Returns true if this node has any child nodes. | ||
boolean | isComposite() | → inherited from CompositeNode |
Returns true as this node can have child nodes. | ||
BuildingBlock | getLastBuildingBlock() | |
Gets the last building block in the glossary document. | ||
Node | getLastChild() | → inherited from CompositeNode |
Gets the last child of the node. | ||
ListCollection | getLists() | → inherited from DocumentBase |
Provides access to the list formatting used in the document. | ||
Node | getNextSibling() | → inherited from Node |
Gets the node immediately following this node. | ||
INodeChangingCallback | getNodeChangingCallback() | → inherited from DocumentBase |
void | setNodeChangingCallback(INodeChangingCallback value) | |
Called when a node is inserted or removed in the document. | ||
int | getNodeType() | |
Returns the |
||
java.awt.Color | getPageColor() | → inherited from DocumentBase |
void | setPageColor(java.awt.Color value) | |
Gets or sets the page color of the document. This property is a simpler version of |
||
CompositeNode | getParentNode() | → inherited from Node |
Gets the immediate parent of this node. | ||
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. | ||
IResourceLoadingCallback | getResourceLoadingCallback() | → inherited from DocumentBase |
void | setResourceLoadingCallback(IResourceLoadingCallback value) | |
Allows to control how external resources are loaded. | ||
StyleCollection | getStyles() | → inherited from DocumentBase |
Returns a collection of styles defined in the document. | ||
IWarningCallback | getWarningCallback() | → inherited from DocumentBase |
void | setWarningCallback(IWarningCallback value) | |
Called during various document processing procedures when an issue is detected that might result in data or formatting fidelity loss. |
Method Summary | ||
---|---|---|
boolean | accept(DocumentVisitor visitor) | |
Accepts a visitor. | ||
Node | appendChild(Node newChild) | → inherited from CompositeNode |
Adds the specified node to the end of the list of child nodes for this node. | ||
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. | ||
BuildingBlock | getBuildingBlock(int gallery, java.lang.String category, java.lang.String name) | |
Finds a building block using the specified gallery, category and name. | ||
Node | getChild(int nodeType, int index, boolean isDeep) | → inherited from CompositeNode |
Returns an Nth child node that matches the specified type. | ||
NodeCollection | getChildNodes(int nodeType, boolean isDeep) | → inherited from CompositeNode |
Returns a live collection of child nodes that match the specified type. | ||
java.lang.String | getText() | → inherited from CompositeNode |
Gets the text of this node and of all its children. | ||
Node | importNode(Node srcNode, boolean isImportChildren) | → inherited from DocumentBase |
Imports a node from another document to the current document. |
||
Node | importNode(Node srcNode, boolean isImportChildren, int importFormatMode) | → inherited from DocumentBase |
Imports a node from another document to the current document with an option to control formatting. |
||
int | indexOf(Node child) | → inherited from CompositeNode |
Returns the index of the specified child node in the child node array. | ||
Node | insertAfter(Node newChild, Node refChild) | → inherited from CompositeNode |
Inserts the specified node immediately after the specified reference node. | ||
Node | insertBefore(Node newChild, Node refChild) | → inherited from CompositeNode |
Inserts the specified node immediately before the specified reference node. | ||
java.util.Iterator<Node> | iterator() | → inherited from CompositeNode |
Provides support for the for each style iteration over the child nodes of this node. | ||
Node | nextPreOrder(Node rootNode) | → inherited from Node |
Gets next node according to the pre-order tree traversal algorithm. | ||
Node | prependChild(Node newChild) | → inherited from CompositeNode |
Adds the specified node to the beginning of the list of child nodes for this node. | ||
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. | ||
void | removeAllChildren() | → inherited from CompositeNode |
Removes all the child nodes of the current node. | ||
Node | removeChild(Node oldChild) | → inherited from CompositeNode |
Removes the specified child node. | ||
void | removeSmartTags() | → inherited from CompositeNode |
Removes all |
||
NodeList | selectNodes(java.lang.String xpath) | → inherited from CompositeNode |
Selects a list of nodes matching the XPath expression. | ||
Node | selectSingleNode(java.lang.String xpath) | → inherited from CompositeNode |
Selects the first Node that matches the XPath expression. | ||
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. |
Constructor Detail |
---|
public GlossaryDocument()
Property Getters/Setters Detail |
---|
getBackgroundShape/setBackgroundShape | → inherited from DocumentBase |
public Shape getBackgroundShape() / public void setBackgroundShape(Shape value) |
Microsoft Word allows only a shape that has its
Microsoft Word supports only the fill properties of a background shape. All other properties are ignored.
Setting this property to a non-null value will also set the
Example:
Shows how to set the background shape of a document.Document doc = new Document(); Assert.assertNull(doc.getBackgroundShape()); // A background shape can only be a rectangle // We will set the color of this rectangle to light blue Shape shapeRectangle = new Shape(doc, ShapeType.RECTANGLE); doc.setBackgroundShape(shapeRectangle); // This rectangle covers the entire page in the output document // We can also do this by setting doc.PageColor shapeRectangle.setFillColor(Color.blue); doc.save(getArtifactsDir() + "DocumentBase.BackgroundShapeFlatColor.docx"); // Setting the image will override the flat background color with the image shapeRectangle.getImageData().setImage(getImageDir() + "Transparent background logo.png"); Assert.assertTrue(doc.getBackgroundShape().hasImage()); // This image is a photo with a white background // To make it suitable as a watermark, we will need to do some image processing // The default values for these variables are 0.5, so here we are lowering the contrast and increasing the brightness shapeRectangle.getImageData().setContrast(0.2); shapeRectangle.getImageData().setBrightness(0.7); // Microsoft Word does not support images in background shapes, so even though we set the background as an image, // the output will show a light blue background like before // However, we can see our watermark in an output pdf doc.save(getArtifactsDir() + "DocumentBase.BackgroundShape.pdf");
getBuildingBlocks | |
public BuildingBlockCollection getBuildingBlocks() |
Example:
Shows how to use GlossaryDocument and BuildingBlockCollection.public void glossaryDocument() throws Exception { Document doc = new Document(); GlossaryDocument glossaryDoc = new GlossaryDocument(); glossaryDoc.appendChild(createNewBuildingBlock(glossaryDoc, "Block 1")); glossaryDoc.appendChild(createNewBuildingBlock(glossaryDoc, "Block 2")); glossaryDoc.appendChild(createNewBuildingBlock(glossaryDoc, "Block 3")); glossaryDoc.appendChild(createNewBuildingBlock(glossaryDoc, "Block 4")); glossaryDoc.appendChild(createNewBuildingBlock(glossaryDoc, "Block 5")); Assert.assertEquals(glossaryDoc.getBuildingBlocks().getCount(), 5); doc.setGlossaryDocument(glossaryDoc); // There is a different ways how to get created building blocks Assert.assertEquals("Block 1", glossaryDoc.getFirstBuildingBlock().getName()); Assert.assertEquals("Block 2", glossaryDoc.getBuildingBlocks().get(1).getName()); Assert.assertEquals("Block 3", glossaryDoc.getBuildingBlocks().toArray()[2].getName()); Assert.assertEquals("Block 4", glossaryDoc.getBuildingBlock(BuildingBlockGallery.ALL, "(Empty Category)", "Block 4").getName()); Assert.assertEquals("Block 5", glossaryDoc.getLastBuildingBlock().getName()); // We will do that using a custom visitor, which also will give every BuildingBlock in the GlossaryDocument a unique GUID GlossaryDocVisitor visitor = new GlossaryDocVisitor(); glossaryDoc.accept(visitor); System.out.println(visitor.getText()); // We can find our new blocks in Microsoft Word via Insert > Quick Parts > Building Blocks Organizer... doc.save(getArtifactsDir() + "BuildingBlocks.GlossaryDocument.dotx"); } public static BuildingBlock createNewBuildingBlock(final GlossaryDocument glossaryDoc, final String buildingBlockName) { BuildingBlock buildingBlock = new BuildingBlock(glossaryDoc); buildingBlock.setName(buildingBlockName); return buildingBlock; } /// <summary> /// Simple implementation of giving each building block in a glossary document a unique GUID. Implemented as a Visitor. /// </summary> public static class GlossaryDocVisitor extends DocumentVisitor { public GlossaryDocVisitor() { mBlocksByGuid = new HashMap<>(); mBuilder = new StringBuilder(); } public String getText() { return mBuilder.toString(); } public HashMap<UUID, BuildingBlock> getDictionary() { return mBlocksByGuid; } public int visitGlossaryDocumentStart(final GlossaryDocument glossary) { mBuilder.append("Glossary document found!\n"); return VisitorAction.CONTINUE; } public int visitGlossaryDocumentEnd(final GlossaryDocument glossary) { mBuilder.append("Reached end of glossary!\n"); mBuilder.append("BuildingBlocks found: " + mBlocksByGuid.size() + "\r\n"); return VisitorAction.CONTINUE; } public int visitBuildingBlockStart(final BuildingBlock block) { block.setGuid(UUID.randomUUID()); mBlocksByGuid.put(block.getGuid(), block); return VisitorAction.CONTINUE; } public int visitBuildingBlockEnd(final BuildingBlock block) { mBuilder.append("\tVisited block \"" + block.getName() + "\"" + "\r\n"); mBuilder.append("\t Type: " + block.getType() + "\r\n"); mBuilder.append("\t Gallery: " + block.getGallery() + "\r\n"); mBuilder.append("\t Behavior: " + block.getBehavior() + "\r\n"); mBuilder.append("\t Description: " + block.getDescription() + "\r\n"); return VisitorAction.CONTINUE; } private HashMap<UUID, BuildingBlock> mBlocksByGuid; private StringBuilder mBuilder; }
getChildNodes | → inherited from CompositeNode |
public NodeCollection getChildNodes() |
Note, GetChildNodes(NodeType.Any, false)
and creates and returns a new collection every time it is accessed.
If there are no child nodes, this property returns an empty collection.
Example:
Shows how to enumerate immediate children of a CompositeNode using the enumerator provided by the ChildNodes collection.NodeCollection children = paragraph.getChildNodes(); for (Node child : (Iterable<Node>) children) { // Paragraph may contain children of various types such as runs, shapes and so on if (child.getNodeType() == NodeType.RUN) { // Say we found the node that we want, do something useful Run run = (Run) child; System.out.println(run.getText()); } }
getCount | → inherited from CompositeNode |
public int getCount() |
Example:
Shows how to add, update and delete child nodes from within a CompositeNode.Document doc = new Document(); // An empty document has one paragraph by default Assert.assertEquals(doc.getFirstSection().getBody().getParagraphs().getCount(), 1); // A paragraph is a composite node because it can contain runs, which are another type of node Paragraph paragraph = doc.getFirstSection().getBody().getFirstParagraph(); Run paragraphText = new Run(doc, "Initial text. "); paragraph.appendChild(paragraphText); // We will place these 3 children into the main text of our paragraph Run run1 = new Run(doc, "Run 1. "); Run run2 = new Run(doc, "Run 2. "); Run run3 = new Run(doc, "Run 3. "); // We initialized them but not in our paragraph yet Assert.assertEquals(paragraph.getText(), "Initial text. " + (char) 12); // Insert run2 before initial paragraph text. This will be at the start of the paragraph paragraph.insertBefore(run2, paragraphText); // Insert run3 after initial paragraph text. This will be at the end of the paragraph paragraph.insertAfter(run3, paragraphText); // Insert run1 before every other child node. run2 was the start of the paragraph, now it will be run1 paragraph.prependChild(run1); Assert.assertEquals(paragraph.getText(), "Run 1. Run 2. Initial text. Run 3. " + (char) 12); Assert.assertEquals(paragraph.getChildNodes(NodeType.ANY, true).getCount(), 4); // Access the child node collection and update/delete children ((Run) paragraph.getChildNodes(NodeType.RUN, true).get(1)).setText("Updated run 2. "); paragraph.getChildNodes(NodeType.RUN, true).remove(paragraphText); Assert.assertEquals(paragraph.getText(), "Run 1. Updated run 2. Run 3. " + (char) 12); Assert.assertEquals(paragraph.getChildNodes(NodeType.ANY, true).getCount(), 3);
getDocument | → inherited from DocumentBase |
public DocumentBase getDocument() |
getFirstBuildingBlock | |
public BuildingBlock getFirstBuildingBlock() |
null
if there are no building blocks available.
Example:
Shows how to use GlossaryDocument and BuildingBlockCollection.public void glossaryDocument() throws Exception { Document doc = new Document(); GlossaryDocument glossaryDoc = new GlossaryDocument(); glossaryDoc.appendChild(createNewBuildingBlock(glossaryDoc, "Block 1")); glossaryDoc.appendChild(createNewBuildingBlock(glossaryDoc, "Block 2")); glossaryDoc.appendChild(createNewBuildingBlock(glossaryDoc, "Block 3")); glossaryDoc.appendChild(createNewBuildingBlock(glossaryDoc, "Block 4")); glossaryDoc.appendChild(createNewBuildingBlock(glossaryDoc, "Block 5")); Assert.assertEquals(glossaryDoc.getBuildingBlocks().getCount(), 5); doc.setGlossaryDocument(glossaryDoc); // There is a different ways how to get created building blocks Assert.assertEquals("Block 1", glossaryDoc.getFirstBuildingBlock().getName()); Assert.assertEquals("Block 2", glossaryDoc.getBuildingBlocks().get(1).getName()); Assert.assertEquals("Block 3", glossaryDoc.getBuildingBlocks().toArray()[2].getName()); Assert.assertEquals("Block 4", glossaryDoc.getBuildingBlock(BuildingBlockGallery.ALL, "(Empty Category)", "Block 4").getName()); Assert.assertEquals("Block 5", glossaryDoc.getLastBuildingBlock().getName()); // We will do that using a custom visitor, which also will give every BuildingBlock in the GlossaryDocument a unique GUID GlossaryDocVisitor visitor = new GlossaryDocVisitor(); glossaryDoc.accept(visitor); System.out.println(visitor.getText()); // We can find our new blocks in Microsoft Word via Insert > Quick Parts > Building Blocks Organizer... doc.save(getArtifactsDir() + "BuildingBlocks.GlossaryDocument.dotx"); } public static BuildingBlock createNewBuildingBlock(final GlossaryDocument glossaryDoc, final String buildingBlockName) { BuildingBlock buildingBlock = new BuildingBlock(glossaryDoc); buildingBlock.setName(buildingBlockName); return buildingBlock; } /// <summary> /// Simple implementation of giving each building block in a glossary document a unique GUID. Implemented as a Visitor. /// </summary> public static class GlossaryDocVisitor extends DocumentVisitor { public GlossaryDocVisitor() { mBlocksByGuid = new HashMap<>(); mBuilder = new StringBuilder(); } public String getText() { return mBuilder.toString(); } public HashMap<UUID, BuildingBlock> getDictionary() { return mBlocksByGuid; } public int visitGlossaryDocumentStart(final GlossaryDocument glossary) { mBuilder.append("Glossary document found!\n"); return VisitorAction.CONTINUE; } public int visitGlossaryDocumentEnd(final GlossaryDocument glossary) { mBuilder.append("Reached end of glossary!\n"); mBuilder.append("BuildingBlocks found: " + mBlocksByGuid.size() + "\r\n"); return VisitorAction.CONTINUE; } public int visitBuildingBlockStart(final BuildingBlock block) { block.setGuid(UUID.randomUUID()); mBlocksByGuid.put(block.getGuid(), block); return VisitorAction.CONTINUE; } public int visitBuildingBlockEnd(final BuildingBlock block) { mBuilder.append("\tVisited block \"" + block.getName() + "\"" + "\r\n"); mBuilder.append("\t Type: " + block.getType() + "\r\n"); mBuilder.append("\t Gallery: " + block.getGallery() + "\r\n"); mBuilder.append("\t Behavior: " + block.getBehavior() + "\r\n"); mBuilder.append("\t Description: " + block.getDescription() + "\r\n"); return VisitorAction.CONTINUE; } private HashMap<UUID, BuildingBlock> mBlocksByGuid; private StringBuilder mBuilder; }
getFirstChild | → inherited from CompositeNode |
public Node getFirstChild() |
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() + "Document.docx"); // 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); } } }
getFontInfos | → inherited from DocumentBase |
public FontInfoCollection getFontInfos() |
This collection of font definitions is loaded as is from the document. Font definitions might be optional, missing or incomplete in some documents.
Do not rely on this collection to ascertain that a particular font is used in the document. You should only use this collection to get information about fonts that might be used in the document.
Example:
Shows how to save a document with embedded TrueType fonts.Document doc = new Document(getMyDir() + "Document.docx"); FontInfoCollection fontInfos = doc.getFontInfos(); fontInfos.setEmbedTrueTypeFonts(true); fontInfos.setEmbedSystemFonts(false); fontInfos.setSaveSubsetFonts(false); doc.save(getArtifactsDir() + "Font.FontInfoCollection.docx");
Example:
Shows how to gather the details of what fonts are present in a document.Document doc = new Document(getMyDir() + "Document.docx"); FontInfoCollection fonts = doc.getFontInfos(); int fontIndex = 1; // The fonts info extracted from this document does not necessarily mean that the fonts themselves are // used in the document. If a font is present but not used then most likely they were referenced at some time // and then removed from the Document for (FontInfo info : fonts) { // Print out some important details about the font System.out.println(MessageFormat.format("Font #{0}", fontIndex)); System.out.println(MessageFormat.format("Name: {0}", info.getName())); System.out.println(MessageFormat.format("IsTrueType: {0}", info.isTrueType())); fontIndex++; }
hasChildNodes | → inherited from CompositeNode |
public boolean hasChildNodes() |
isComposite | → inherited from CompositeNode |
public boolean isComposite() |
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() + "Document.docx"); // 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); } } }
getLastBuildingBlock | |
public BuildingBlock getLastBuildingBlock() |
null
if there are no building blocks available.
Example:
Shows how to use GlossaryDocument and BuildingBlockCollection.public void glossaryDocument() throws Exception { Document doc = new Document(); GlossaryDocument glossaryDoc = new GlossaryDocument(); glossaryDoc.appendChild(createNewBuildingBlock(glossaryDoc, "Block 1")); glossaryDoc.appendChild(createNewBuildingBlock(glossaryDoc, "Block 2")); glossaryDoc.appendChild(createNewBuildingBlock(glossaryDoc, "Block 3")); glossaryDoc.appendChild(createNewBuildingBlock(glossaryDoc, "Block 4")); glossaryDoc.appendChild(createNewBuildingBlock(glossaryDoc, "Block 5")); Assert.assertEquals(glossaryDoc.getBuildingBlocks().getCount(), 5); doc.setGlossaryDocument(glossaryDoc); // There is a different ways how to get created building blocks Assert.assertEquals("Block 1", glossaryDoc.getFirstBuildingBlock().getName()); Assert.assertEquals("Block 2", glossaryDoc.getBuildingBlocks().get(1).getName()); Assert.assertEquals("Block 3", glossaryDoc.getBuildingBlocks().toArray()[2].getName()); Assert.assertEquals("Block 4", glossaryDoc.getBuildingBlock(BuildingBlockGallery.ALL, "(Empty Category)", "Block 4").getName()); Assert.assertEquals("Block 5", glossaryDoc.getLastBuildingBlock().getName()); // We will do that using a custom visitor, which also will give every BuildingBlock in the GlossaryDocument a unique GUID GlossaryDocVisitor visitor = new GlossaryDocVisitor(); glossaryDoc.accept(visitor); System.out.println(visitor.getText()); // We can find our new blocks in Microsoft Word via Insert > Quick Parts > Building Blocks Organizer... doc.save(getArtifactsDir() + "BuildingBlocks.GlossaryDocument.dotx"); } public static BuildingBlock createNewBuildingBlock(final GlossaryDocument glossaryDoc, final String buildingBlockName) { BuildingBlock buildingBlock = new BuildingBlock(glossaryDoc); buildingBlock.setName(buildingBlockName); return buildingBlock; } /// <summary> /// Simple implementation of giving each building block in a glossary document a unique GUID. Implemented as a Visitor. /// </summary> public static class GlossaryDocVisitor extends DocumentVisitor { public GlossaryDocVisitor() { mBlocksByGuid = new HashMap<>(); mBuilder = new StringBuilder(); } public String getText() { return mBuilder.toString(); } public HashMap<UUID, BuildingBlock> getDictionary() { return mBlocksByGuid; } public int visitGlossaryDocumentStart(final GlossaryDocument glossary) { mBuilder.append("Glossary document found!\n"); return VisitorAction.CONTINUE; } public int visitGlossaryDocumentEnd(final GlossaryDocument glossary) { mBuilder.append("Reached end of glossary!\n"); mBuilder.append("BuildingBlocks found: " + mBlocksByGuid.size() + "\r\n"); return VisitorAction.CONTINUE; } public int visitBuildingBlockStart(final BuildingBlock block) { block.setGuid(UUID.randomUUID()); mBlocksByGuid.put(block.getGuid(), block); return VisitorAction.CONTINUE; } public int visitBuildingBlockEnd(final BuildingBlock block) { mBuilder.append("\tVisited block \"" + block.getName() + "\"" + "\r\n"); mBuilder.append("\t Type: " + block.getType() + "\r\n"); mBuilder.append("\t Gallery: " + block.getGallery() + "\r\n"); mBuilder.append("\t Behavior: " + block.getBehavior() + "\r\n"); mBuilder.append("\t Description: " + block.getDescription() + "\r\n"); return VisitorAction.CONTINUE; } private HashMap<UUID, BuildingBlock> mBlocksByGuid; private StringBuilder mBuilder; }
getLastChild | → inherited from CompositeNode |
public Node getLastChild() |
Example:
Shows how to 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); }
getLists | → inherited from DocumentBase |
public ListCollection getLists() |
For more information see the description of the
Example:
Shows how to specify list level number when building a list using DocumentBuilder.Document doc = new Document(); DocumentBuilder builder = new DocumentBuilder(doc); // Create a numbered list based on one of the Microsoft Word list templates and // apply it to the current paragraph in the document builder builder.getListFormat().setList(doc.getLists().add(ListTemplate.NUMBER_ARABIC_DOT)); // There are 9 levels in this list, lets try them all for (int i = 0; i < 9; i++) { builder.getListFormat().setListLevelNumber(i); builder.writeln("Level " + i); } // Create a bulleted list based on one of the Microsoft Word list templates // and apply it to the current paragraph in the document builder builder.getListFormat().setList(doc.getLists().add(ListTemplate.BULLET_DIAMONDS)); // There are 9 levels in this list, lets try them all for (int i = 0; i < 9; i++) { builder.getListFormat().setListLevelNumber(i); builder.writeln("Level " + i); } // This is a way to stop list formatting builder.getListFormat().setList(null); builder.getDocument().save(getArtifactsDir() + "Lists.SpecifyListLevel.doc");
getNextSibling | → inherited from Node |
public Node getNextSibling() |
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() + "Document.docx"); // 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); } } }
getNodeChangingCallback/setNodeChangingCallback | → inherited from DocumentBase |
public INodeChangingCallback getNodeChangingCallback() / public void setNodeChangingCallback(INodeChangingCallback value) |
Example:
Shows how to implement custom logic over node insertion in the document by changing the font of inserted HTML content.public void fontChangeViaCallback() throws Exception { Document doc = new Document(); DocumentBuilder builder = new DocumentBuilder(doc); // Set up and pass the object which implements the handler methods doc.setNodeChangingCallback(new HandleNodeChangingFontChanger()); // Insert sample HTML content builder.insertHtml("<p>Hello World</p>"); doc.save(getArtifactsDir() + "Document.FontChangeViaCallback.docx"); } public class HandleNodeChangingFontChanger implements INodeChangingCallback { // Implement the NodeInserted handler to set default font settings for every Run node inserted into the Document public void nodeInserted(final NodeChangingArgs args) { // Change the font of inserted text contained in the Run nodes if (args.getNode().getNodeType() == NodeType.RUN) { Font font = ((Run) args.getNode()).getFont(); font.setSize(24); font.setName("Arial"); } } public void nodeInserting(final NodeChangingArgs args) { // Do Nothing } public void nodeRemoved(final NodeChangingArgs args) { // Do Nothing } public void nodeRemoving(final NodeChangingArgs args) { // Do Nothing } }
getNodeType | |
public int getNodeType() |
Example:
Shows how to retrieve the NodeType enumeration of nodes.Document doc = new Document(getMyDir() + "Document.docx"); // 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()));
getPageColor/setPageColor | → inherited from DocumentBase |
public java.awt.Color getPageColor() / public void setPageColor(java.awt.Color value) |
This property provides a simple way to specify a solid page color for the document.
Setting this property creates and sets an appropriate
If the page color is not set (e.g. there is no background shape in the document) returns a zero color.
Example:
Shows how to set the page color.Document doc = new Document(); doc.setPageColor(Color.lightGray); doc.save(getArtifactsDir() + "DocumentBase.SetPageColor.docx");
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.// 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));
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 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 | → 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());
getResourceLoadingCallback/setResourceLoadingCallback | → inherited from DocumentBase |
public IResourceLoadingCallback getResourceLoadingCallback() / public void setResourceLoadingCallback(IResourceLoadingCallback value) |
Example:
Shows how to process inserted resources differently.public void resourceLoadingCallback() throws Exception { Document doc = new Document(); // Enable our custom image loading doc.setResourceLoadingCallback(new ImageNameHandler()); DocumentBuilder builder = new DocumentBuilder(doc); // We usually insert images as a uri or byte array, but there are many other possibilities with ResourceLoadingCallback // In this case we are referencing images with simple names and keep the image fetching logic somewhere else builder.insertImage("Google Logo"); builder.insertImage("Aspose Logo"); builder.insertImage("My Watermark"); // Images belong to Shape objects, which are placed and scaled in the document Assert.assertEquals(3, doc.getChildNodes(NodeType.SHAPE, true).getCount()); doc.save(getArtifactsDir() + "DocumentBase.ResourceLoadingCallback.docx"); } private static class ImageNameHandler implements IResourceLoadingCallback { public int resourceLoading(final ResourceLoadingArgs args) throws URISyntaxException, IOException { if (args.getResourceType() == ResourceType.IMAGE) { // builder.InsertImage expects a uri so inputs like "Google Logo" would normally trigger a FileNotFoundException // We can still process those inputs and find an image any way we like, as long as an image byte array is passed to args.SetData() if ("Google Logo".equals(args.getOriginalUri())) { args.setData(DocumentHelper.getBytesFromStream(new URI("http://www.google.com/images/logos/ps_logo2.png").toURL().openStream())); // We need this return statement any time a resource is loaded in a custom manner return ResourceLoadingAction.USER_PROVIDED; } if ("Aspose Logo".equals(args.getOriginalUri())) { args.setData(DocumentHelper.getBytesFromStream(getAsposelogoUri().toURL().openStream())); return ResourceLoadingAction.USER_PROVIDED; } // We can find and add an image any way we like, as long as args.SetData() is called with some image byte array as a parameter if ("My Watermark".equals(args.getOriginalUri())) { InputStream imageStream = new FileInputStream(getImageDir() + "Transparent background logo.png"); args.setData(DocumentHelper.getBytesFromStream(imageStream)); return ResourceLoadingAction.USER_PROVIDED; } } // All other resources such as documents, CSS stylesheets and images passed as uris are handled as they were normally return ResourceLoadingAction.DEFAULT; } }
getStyles | → inherited from DocumentBase |
public StyleCollection getStyles() |
For more information see the description of the
Example:
Shows how to get access to the collection of styles defined in the document.Document doc = new Document(); Iterator<Style> stylesEnum = doc.getStyles().iterator(); while (stylesEnum.hasNext()) { Style curStyle = stylesEnum.next(); System.out.println(MessageFormat.format("Style name:\t\"{0}\", of type \"{1}\"", curStyle.getName(), curStyle.getType())); System.out.println(MessageFormat.format("\tSubsequent style:\t{0}", curStyle.getNextParagraphStyleName())); System.out.println(MessageFormat.format("\tIs heading:\t\t\t{0}", curStyle.isHeading())); System.out.println(MessageFormat.format("\tIs QuickStyle:\t\t{0}", curStyle.isQuickStyle())); Assert.assertEquals(curStyle.getDocument(), doc); }
Example:
Shows how to create and use a paragraph style with list formatting.Document doc = new Document(); DocumentBuilder builder = new DocumentBuilder(doc); // Create a paragraph style and specify some formatting for it Style style = doc.getStyles().add(StyleType.PARAGRAPH, "MyStyle1"); style.getFont().setSize(24); style.getFont().setName("Verdana"); style.getParagraphFormat().setSpaceAfter(12); // Create a list and make sure the paragraphs that use this style will use this list style.getListFormat().setList(doc.getLists().add(ListTemplate.BULLET_DEFAULT)); style.getListFormat().setListLevelNumber(0); // Apply the paragraph style to the current paragraph in the document and add some text builder.getParagraphFormat().setStyle(style); builder.writeln("Hello World: MyStyle1, bulleted."); // Change to a paragraph style that has no list formatting builder.getParagraphFormat().setStyle(doc.getStyles().get("Normal")); builder.writeln("Hello World: Normal."); builder.getDocument().save(getArtifactsDir() + "Lists.ParagraphStyleBulleted.doc");
getWarningCallback/setWarningCallback | → inherited from DocumentBase |
public IWarningCallback getWarningCallback() / public void setWarningCallback(IWarningCallback value) |
Example:
Shows how to implement the IWarningCallback to be notified of any font substitution during document save.public static class HandleDocumentWarnings implements IWarningCallback { /** * Our callback only needs to implement the "Warning" method. This method is called whenever there is a * potential issue during document processing. The callback can be set to listen for warnings generated during document * load and/or document save. */ public void warning(final WarningInfo info) { // We are only interested in fonts being substituted if (info.getWarningType() == WarningType.FONT_SUBSTITUTION) { System.out.println("Font substitution: " + info.getDescription()); } } }
Example:
Demonstrates how to receive notifications of font substitutions by using IWarningCallback.// Load the document to render Document doc = new Document(getMyDir() + "Document.docx"); // Create a new class implementing IWarningCallback and assign it to the PdfSaveOptions class HandleDocumentWarnings callback = new HandleDocumentWarnings(); doc.setWarningCallback(callback); // We can choose the default font to use in the case of any missing fonts FontSettings.getDefaultInstance().getSubstitutionSettings().getDefaultFontSubstitution().setDefaultFontName("Arial"); // For testing we will set Aspose.Words to look for fonts only in a folder which doesn't exist. Since Aspose.Words won't // find any fonts in the specified directory, then during rendering the fonts in the document will be substituted with the default // font specified under FontSettings.DefaultFontName. We can pick up on this substitution using our callback FontSettings.getDefaultInstance().setFontsFolder("", false); // Pass the save options along with the save path to the save method doc.save(getArtifactsDir() + "Font.SubstitutionNotification.pdf");
Method Detail |
---|
accept | |
public boolean accept(DocumentVisitor visitor) throws java.lang.Exception |
Enumerates over this node and all of its children. Each node calls a corresponding method on DocumentVisitor.
For more info see the Visitor design pattern.
Calls
Note: A glossary document node and its children are not visited when you execute a
Visitor over a
visitor
- The visitor that will visit the nodes.Example:
Shows how to use GlossaryDocument and BuildingBlockCollection.public void glossaryDocument() throws Exception { Document doc = new Document(); GlossaryDocument glossaryDoc = new GlossaryDocument(); glossaryDoc.appendChild(createNewBuildingBlock(glossaryDoc, "Block 1")); glossaryDoc.appendChild(createNewBuildingBlock(glossaryDoc, "Block 2")); glossaryDoc.appendChild(createNewBuildingBlock(glossaryDoc, "Block 3")); glossaryDoc.appendChild(createNewBuildingBlock(glossaryDoc, "Block 4")); glossaryDoc.appendChild(createNewBuildingBlock(glossaryDoc, "Block 5")); Assert.assertEquals(glossaryDoc.getBuildingBlocks().getCount(), 5); doc.setGlossaryDocument(glossaryDoc); // There is a different ways how to get created building blocks Assert.assertEquals("Block 1", glossaryDoc.getFirstBuildingBlock().getName()); Assert.assertEquals("Block 2", glossaryDoc.getBuildingBlocks().get(1).getName()); Assert.assertEquals("Block 3", glossaryDoc.getBuildingBlocks().toArray()[2].getName()); Assert.assertEquals("Block 4", glossaryDoc.getBuildingBlock(BuildingBlockGallery.ALL, "(Empty Category)", "Block 4").getName()); Assert.assertEquals("Block 5", glossaryDoc.getLastBuildingBlock().getName()); // We will do that using a custom visitor, which also will give every BuildingBlock in the GlossaryDocument a unique GUID GlossaryDocVisitor visitor = new GlossaryDocVisitor(); glossaryDoc.accept(visitor); System.out.println(visitor.getText()); // We can find our new blocks in Microsoft Word via Insert > Quick Parts > Building Blocks Organizer... doc.save(getArtifactsDir() + "BuildingBlocks.GlossaryDocument.dotx"); } public static BuildingBlock createNewBuildingBlock(final GlossaryDocument glossaryDoc, final String buildingBlockName) { BuildingBlock buildingBlock = new BuildingBlock(glossaryDoc); buildingBlock.setName(buildingBlockName); return buildingBlock; } /// <summary> /// Simple implementation of giving each building block in a glossary document a unique GUID. Implemented as a Visitor. /// </summary> public static class GlossaryDocVisitor extends DocumentVisitor { public GlossaryDocVisitor() { mBlocksByGuid = new HashMap<>(); mBuilder = new StringBuilder(); } public String getText() { return mBuilder.toString(); } public HashMap<UUID, BuildingBlock> getDictionary() { return mBlocksByGuid; } public int visitGlossaryDocumentStart(final GlossaryDocument glossary) { mBuilder.append("Glossary document found!\n"); return VisitorAction.CONTINUE; } public int visitGlossaryDocumentEnd(final GlossaryDocument glossary) { mBuilder.append("Reached end of glossary!\n"); mBuilder.append("BuildingBlocks found: " + mBlocksByGuid.size() + "\r\n"); return VisitorAction.CONTINUE; } public int visitBuildingBlockStart(final BuildingBlock block) { block.setGuid(UUID.randomUUID()); mBlocksByGuid.put(block.getGuid(), block); return VisitorAction.CONTINUE; } public int visitBuildingBlockEnd(final BuildingBlock block) { mBuilder.append("\tVisited block \"" + block.getName() + "\"" + "\r\n"); mBuilder.append("\t Type: " + block.getType() + "\r\n"); mBuilder.append("\t Gallery: " + block.getGallery() + "\r\n"); mBuilder.append("\t Behavior: " + block.getBehavior() + "\r\n"); mBuilder.append("\t Description: " + block.getDescription() + "\r\n"); return VisitorAction.CONTINUE; } private HashMap<UUID, BuildingBlock> mBlocksByGuid; private StringBuilder mBuilder; }
appendChild | → inherited from CompositeNode |
public Node appendChild(Node newChild) |
If the newChild is already in the tree, it is first removed.
If the node being inserted was created from another document, you should use
newChild
- The node to add.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");
deepClone | → inherited from Node |
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 | → 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"); int tableIndex = 0; for (Table table : (Iterable<Table>) doc.getChildNodes(NodeType.TABLE, true)) { // First lets find if any cells in the table have tables themselves as children int count = getChildTableCount(table); System.out.println(MessageFormat.format("Table #{0} has {1} tables directly within its cells", tableIndex, count)); // Now let's try the other way around, lets try find if the table is nested inside another table and at what depth int tableDepth = getNestedDepthOfTable(table); if (tableDepth > 0) { System.out.println(MessageFormat.format("Table #{0} is nested inside another table at depth of {1}", tableIndex, tableDepth)); } else { System.out.println(MessageFormat.format("Table #{0} is a non nested table (is not a child of another table)", tableIndex)); } tableIndex++; } } /** * Calculates what level a table is nested inside other tables. * * @returns An integer containing the level the table is nested at. * 0 = Table is not nested inside any other table * 1 = Table is nested within one parent table * 2 = Table is nested within two parent tables etc.. */ private static int getNestedDepthOfTable(final Table table) { int depth = 0; int type = table.getNodeType(); // The parent of the table will be a Cell, instead attempt to find a grandparent that is of type Table Node parent = table.getAncestor(table.getNodeType()); while (parent != null) { // Every time we find a table a level up we increase the depth counter and then try to find an // ancestor of type table from the parent depth++; parent = parent.getAncestor(Table.class); } return depth; } /** * Determines if a table contains any immediate child table within its cells. * Does not recursively traverse through those tables to check for further tables. * * @returns Returns true if at least one child cell contains a table. * Returns false if no cells in the table contains a table. */ private static int getChildTableCount(final Table table) { int tableCount = 0; // Iterate through all child rows in the table for (Row row : table.getRows()) { // Iterate through all child cells in the row for (Cell cell : row.getCells()) { // Retrieve the collection of child tables of this cell TableCollection childTables = cell.getTables(); // If this cell has a table as a child then return true if (childTables.getCount() > 0) tableCount++; } } // No cell contains a table return tableCount; }
getAncestor | → 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"); int tableIndex = 0; for (Table table : (Iterable<Table>) doc.getChildNodes(NodeType.TABLE, true)) { // First lets find if any cells in the table have tables themselves as children int count = getChildTableCount(table); System.out.println(MessageFormat.format("Table #{0} has {1} tables directly within its cells", tableIndex, count)); // Now let's try the other way around, lets try find if the table is nested inside another table and at what depth int tableDepth = getNestedDepthOfTable(table); if (tableDepth > 0) { System.out.println(MessageFormat.format("Table #{0} is nested inside another table at depth of {1}", tableIndex, tableDepth)); } else { System.out.println(MessageFormat.format("Table #{0} is a non nested table (is not a child of another table)", tableIndex)); } tableIndex++; } } /** * Calculates what level a table is nested inside other tables. * * @returns An integer containing the level the table is nested at. * 0 = Table is not nested inside any other table * 1 = Table is nested within one parent table * 2 = Table is nested within two parent tables etc.. */ private static int getNestedDepthOfTable(final Table table) { int depth = 0; int type = table.getNodeType(); // The parent of the table will be a Cell, instead attempt to find a grandparent that is of type Table Node parent = table.getAncestor(table.getNodeType()); while (parent != null) { // Every time we find a table a level up we increase the depth counter and then try to find an // ancestor of type table from the parent depth++; parent = parent.getAncestor(Table.class); } return depth; } /** * Determines if a table contains any immediate child table within its cells. * Does not recursively traverse through those tables to check for further tables. * * @returns Returns true if at least one child cell contains a table. * Returns false if no cells in the table contains a table. */ private static int getChildTableCount(final Table table) { int tableCount = 0; // Iterate through all child rows in the table for (Row row : table.getRows()) { // Iterate through all child cells in the row for (Cell cell : row.getCells()) { // Retrieve the collection of child tables of this cell TableCollection childTables = cell.getTables(); // If this cell has a table as a child then return true if (childTables.getCount() > 0) tableCount++; } } // No cell contains a table return tableCount; }
getBuildingBlock | |
public BuildingBlock getBuildingBlock(int gallery, java.lang.String category, java.lang.String name) |
This is a convenience method that iterates over all building blocks in this collection and returns the first building block that matches the specified gallery, category and name.
Microsoft Word organizes building blocks into galleries. The galleries
are predefined using the
gallery
- A category
- The category criteria. Can be null, in which case it will not be used for comparison.name
- The building block name criteria.Example:
Shows how to use GlossaryDocument and BuildingBlockCollection.public void glossaryDocument() throws Exception { Document doc = new Document(); GlossaryDocument glossaryDoc = new GlossaryDocument(); glossaryDoc.appendChild(createNewBuildingBlock(glossaryDoc, "Block 1")); glossaryDoc.appendChild(createNewBuildingBlock(glossaryDoc, "Block 2")); glossaryDoc.appendChild(createNewBuildingBlock(glossaryDoc, "Block 3")); glossaryDoc.appendChild(createNewBuildingBlock(glossaryDoc, "Block 4")); glossaryDoc.appendChild(createNewBuildingBlock(glossaryDoc, "Block 5")); Assert.assertEquals(glossaryDoc.getBuildingBlocks().getCount(), 5); doc.setGlossaryDocument(glossaryDoc); // There is a different ways how to get created building blocks Assert.assertEquals("Block 1", glossaryDoc.getFirstBuildingBlock().getName()); Assert.assertEquals("Block 2", glossaryDoc.getBuildingBlocks().get(1).getName()); Assert.assertEquals("Block 3", glossaryDoc.getBuildingBlocks().toArray()[2].getName()); Assert.assertEquals("Block 4", glossaryDoc.getBuildingBlock(BuildingBlockGallery.ALL, "(Empty Category)", "Block 4").getName()); Assert.assertEquals("Block 5", glossaryDoc.getLastBuildingBlock().getName()); // We will do that using a custom visitor, which also will give every BuildingBlock in the GlossaryDocument a unique GUID GlossaryDocVisitor visitor = new GlossaryDocVisitor(); glossaryDoc.accept(visitor); System.out.println(visitor.getText()); // We can find our new blocks in Microsoft Word via Insert > Quick Parts > Building Blocks Organizer... doc.save(getArtifactsDir() + "BuildingBlocks.GlossaryDocument.dotx"); } public static BuildingBlock createNewBuildingBlock(final GlossaryDocument glossaryDoc, final String buildingBlockName) { BuildingBlock buildingBlock = new BuildingBlock(glossaryDoc); buildingBlock.setName(buildingBlockName); return buildingBlock; } /// <summary> /// Simple implementation of giving each building block in a glossary document a unique GUID. Implemented as a Visitor. /// </summary> public static class GlossaryDocVisitor extends DocumentVisitor { public GlossaryDocVisitor() { mBlocksByGuid = new HashMap<>(); mBuilder = new StringBuilder(); } public String getText() { return mBuilder.toString(); } public HashMap<UUID, BuildingBlock> getDictionary() { return mBlocksByGuid; } public int visitGlossaryDocumentStart(final GlossaryDocument glossary) { mBuilder.append("Glossary document found!\n"); return VisitorAction.CONTINUE; } public int visitGlossaryDocumentEnd(final GlossaryDocument glossary) { mBuilder.append("Reached end of glossary!\n"); mBuilder.append("BuildingBlocks found: " + mBlocksByGuid.size() + "\r\n"); return VisitorAction.CONTINUE; } public int visitBuildingBlockStart(final BuildingBlock block) { block.setGuid(UUID.randomUUID()); mBlocksByGuid.put(block.getGuid(), block); return VisitorAction.CONTINUE; } public int visitBuildingBlockEnd(final BuildingBlock block) { mBuilder.append("\tVisited block \"" + block.getName() + "\"" + "\r\n"); mBuilder.append("\t Type: " + block.getType() + "\r\n"); mBuilder.append("\t Gallery: " + block.getGallery() + "\r\n"); mBuilder.append("\t Behavior: " + block.getBehavior() + "\r\n"); mBuilder.append("\t Description: " + block.getDescription() + "\r\n"); return VisitorAction.CONTINUE; } private HashMap<UUID, BuildingBlock> mBlocksByGuid; private StringBuilder mBuilder; }
getChild | → inherited from CompositeNode |
public Node getChild(int nodeType, int index, boolean isDeep) |
If index is out of range, a null is returned.
nodeType
- A index
- Zero based index of the child node to select.
Negative indexes are also allowed and indicate access from the end,
that is -1 means the last node.isDeep
- True to select from all child nodes recursively.
False to select only among immediate children. See remarks for more info.Example:
Shows how to test if a node is inside a field by using an XPath expression.// Let's pick a document we know has some fields in Document doc = new Document(getMyDir() + "Mail merge destination - Northwind employees.docx"); // Let's say we want to check if the Run below is inside a field Run run = (Run) doc.getChild(NodeType.RUN, 5, true); // Evaluate the XPath expression. The resulting NodeList will contain all nodes found inside a field a field (between FieldStart // and FieldEnd exclusive). There can however be FieldStart and FieldEnd nodes in the list if there are nested fields // in the path. Currently does not find rare fields in which the FieldCode or FieldResult spans across multiple paragraphs NodeList resultList = doc.selectNodes("//FieldStart/following-sibling::node()[following-sibling::FieldEnd]"); // Check if the specified run is one of the nodes that are inside the field for (Node node : (Iterable<Node>) resultList) { if (node == run) { System.out.println("The node is found inside a field"); break; } }
Example:
Shows how to extract a specific child node from a CompositeNode by using the GetChild method and passing the NodeType and index.Paragraph paragraph = (Paragraph) doc.getChild(NodeType.PARAGRAPH, 0, true);
getChildNodes | → inherited from CompositeNode |
public NodeCollection getChildNodes(int nodeType, boolean isDeep) |
The collection of nodes returned by this method is always live.
A live collection is always in sync with the document. For example, if you selected all sections in a document and enumerate through the collection deleting the sections, the section is removed from the collection immediately when it is removed from the document.
nodeType
- A isDeep
- True to select from all child nodes recursively.
False to select only among immediate children. Example:
Shows how to get all comments with all replies.Document doc = new Document(getMyDir() + "Comments.docx"); // Get all comment from the document NodeCollection comments = doc.getChildNodes(NodeType.COMMENT, true); // For all comments and replies we identify comment level and info about it for (Comment comment : (Iterable<Comment>) comments) { if (comment.getAncestor() == null) { System.out.println("\nThis is a top-level comment"); System.out.println("Comment author: " + comment.getAuthor()); System.out.println("Comment text: " + comment.getText()); for (Comment commentReply : comment.getReplies()) { System.out.println("\n\tThis is a comment reply"); System.out.println("\tReply author: " + commentReply.getAuthor()); System.out.println("\tReply text: " + commentReply.getText()); } } }
Example:
Shows how to extract images from a document and save them as files.public void extractImagesToFiles() throws Exception { Document doc = new Document(getMyDir() + "Images.docx"); NodeCollection shapes = doc.getChildNodes(NodeType.SHAPE, true); int imageIndex = 0; for (Shape shape : (Iterable<Shape>) shapes) { if (shape.hasImage()) { String imageFileName = MessageFormat.format("File.ExtractImagesToFiles.{0}{1}", imageIndex, FileFormatUtil.imageTypeToExtension(shape.getImageData().getImageType())); shape.getImageData().save(getArtifactsDir() + imageFileName); imageIndex++; } } }
Example:
Demonstrates how to remove a specified TOC from a document.// Open a document which contains a TOC Document doc = new Document(getMyDir() + "Table of contents.docx"); // Remove the first TOC from the document Field tocField = doc.getRange().getFields().get(0); tocField.remove(); // Save the output doc.save(getArtifactsDir() + "Field.RemoveTocFromDocument.docx");
getText | → inherited from CompositeNode |
public java.lang.String getText() |
The returned string includes all control and special characters as described in
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));
Example:
Finds and outputs all paragraphs in a document that are bulleted or numbered.NodeCollection paras = doc.getChildNodes(NodeType.PARAGRAPH, true); for (Paragraph para : (Iterable<Paragraph>) paras) { if (para.getListFormat().isListItem()) { System.out.println(java.text.MessageFormat.format("*** A paragraph belongs to list {0}", para.getListFormat().getList().getListId())); System.out.println(para.getText()); } }
importNode | → inherited from DocumentBase |
public Node importNode(Node srcNode, boolean isImportChildren) |
Imports a node from another document to the current document.
This method uses the
Importing a node creates a copy of the source node belonging to the importing document. The returned node has no parent. The source node is not altered or removed from the original document.
Before a node from another document can be inserted into this document, it must be imported.
During import, document-specific properties such as references to styles and lists are translated
from the original to the importing document. After the node was imported, it can be inserted
into the appropriate place in the document using
If the source node already belongs to the destination document, then simply a deep clone of the source node is created.
srcNode
- The node being imported.isImportChildren
- True to import all child nodes recursively; otherwise, false.Example:
Shows how to import node from source document to destination document.Document src = new Document(); Document dst = new Document(); // Add text to both documents src.getFirstSection().getBody().getFirstParagraph().appendChild(new Run(src, "Source document first paragraph text.")); dst.getFirstSection().getBody().getFirstParagraph().appendChild(new Run(dst, "Destination document first paragraph text.")); // In order for a child node to be successfully appended to another node in a document, // both nodes must have the same parent document, or an exception is thrown Assert.assertNotEquals(dst, src.getFirstSection().getDocument()); Assert.assertThrows(IllegalArgumentException.class, () -> dst.appendChild(src.getFirstSection())); // For that reason, we can't just append a section of the source document to the destination document using Node.AppendChild() // Document.ImportNode() lets us get around this by creating a clone of a node and sets its parent to the calling document Section importedSection = (Section)dst.importNode(src.getFirstSection(), true); // Now it is ready to be placed in the document dst.appendChild(importedSection); // Our document now contains both the original and imported section Assert.assertEquals("Destination document first paragraph text.\r\nSource document first paragraph text.\r\n", dst.toString(SaveFormat.TEXT));
importNode | → inherited from DocumentBase |
public Node importNode(Node srcNode, boolean isImportChildren, int importFormatMode) |
Imports a node from another document to the current document with an option to control formatting.
This overload is useful to control how styles and list formatting are imported.
Importing a node creates a copy of the source node belonging to the importing document. The returned node has no parent. The source node is not altered or removed from the original document.
Before a node from another document can be inserted into this document, it must be imported.
During import, document-specific properties such as references to styles and lists are translated
from the original to the importing document. After the node was imported, it can be inserted
into the appropriate place in the document using
If the source node already belongs to the destination document, then simply a deep clone of the source node is created.
srcNode
- The node to imported.isImportChildren
- True to import all child nodes recursively; otherwise, false.importFormatMode
- A Example:
Shows how to import node from source document to destination document with specific options.// Create two documents with two styles that differ in font but have the same name Document src = new Document(); Style srcStyle = src.getStyles().add(StyleType.CHARACTER, "My style"); srcStyle.getFont().setName("Courier New"); DocumentBuilder srcBuilder = new DocumentBuilder(src); srcBuilder.getFont().setStyle(srcStyle); srcBuilder.writeln("Source document text."); Document dst = new Document(); Style dstStyle = dst.getStyles().add(StyleType.CHARACTER, "My style"); dstStyle.getFont().setName("Calibri"); DocumentBuilder dstBuilder = new DocumentBuilder(dst); dstBuilder.getFont().setStyle(dstStyle); dstBuilder.writeln("Destination document text."); // Import the Section from the destination document into the source document, causing a style name collision // If we use destination styles then the imported source text with the same style name as destination text // will adopt the destination style Section importedSection = (Section)dst.importNode(src.getFirstSection(), true, ImportFormatMode.USE_DESTINATION_STYLES); Assert.assertEquals(dstStyle.getFont().getName(), importedSection.getBody().getFirstParagraph().getRuns().get(0).getFont().getName()); Assert.assertEquals(dstStyle.getName(), importedSection.getBody().getFirstParagraph().getRuns().get(0).getFont().getStyleName()); // If we use ImportFormatMode.KeepDifferentStyles, // the source style is preserved and the naming clash is resolved by adding a suffix dst.importNode(src.getFirstSection(), true, ImportFormatMode.KEEP_DIFFERENT_STYLES); Assert.assertEquals(dstStyle.getFont().getName(), dst.getStyles().get("My style").getFont().getName()); Assert.assertEquals(srcStyle.getFont().getName(), dst.getStyles().get("My style_0").getFont().getName());
indexOf | → inherited from CompositeNode |
public int indexOf(Node child) |
Example:
Shows how to get the index of a given child node from its parent.Document doc = new Document(getMyDir() + "Rendering.docx"); // Get the body of the first section in the document Body body = doc.getFirstSection().getBody(); // Retrieve the index of the last paragraph in the body int index = body.getChildNodes().indexOf(body.getLastParagraph());
insertAfter | → inherited from CompositeNode |
public Node insertAfter(Node newChild, Node refChild) |
If refChild is null, inserts newChild at the beginning of the list of child nodes.
If the newChild is already in the tree, it is first removed.
If the node being inserted was created from another document, you should use
newChild
- The Node to insert.refChild
- The Node that is the reference node. The newNode is placed after the refNode. Example:
Shows how to add, update and delete child nodes from within a CompositeNode.Document doc = new Document(); // An empty document has one paragraph by default Assert.assertEquals(doc.getFirstSection().getBody().getParagraphs().getCount(), 1); // A paragraph is a composite node because it can contain runs, which are another type of node Paragraph paragraph = doc.getFirstSection().getBody().getFirstParagraph(); Run paragraphText = new Run(doc, "Initial text. "); paragraph.appendChild(paragraphText); // We will place these 3 children into the main text of our paragraph Run run1 = new Run(doc, "Run 1. "); Run run2 = new Run(doc, "Run 2. "); Run run3 = new Run(doc, "Run 3. "); // We initialized them but not in our paragraph yet Assert.assertEquals(paragraph.getText(), "Initial text. " + (char) 12); // Insert run2 before initial paragraph text. This will be at the start of the paragraph paragraph.insertBefore(run2, paragraphText); // Insert run3 after initial paragraph text. This will be at the end of the paragraph paragraph.insertAfter(run3, paragraphText); // Insert run1 before every other child node. run2 was the start of the paragraph, now it will be run1 paragraph.prependChild(run1); Assert.assertEquals(paragraph.getText(), "Run 1. Run 2. Initial text. Run 3. " + (char) 12); Assert.assertEquals(paragraph.getChildNodes(NodeType.ANY, true).getCount(), 4); // Access the child node collection and update/delete children ((Run) paragraph.getChildNodes(NodeType.RUN, true).get(1)).setText("Updated run 2. "); paragraph.getChildNodes(NodeType.RUN, true).remove(paragraphText); Assert.assertEquals(paragraph.getText(), "Run 1. Updated run 2. Run 3. " + (char) 12); Assert.assertEquals(paragraph.getChildNodes(NodeType.ANY, true).getCount(), 3);
Example:
Shows how to replace all textboxes with images.Document doc = new Document(getMyDir() + "Textboxes in drawing canvas.docx"); // This gets a live collection of all shape nodes in the document NodeCollection shapeCollection = doc.getChildNodes(NodeType.SHAPE, true); // Since we will be adding/removing nodes, it is better to copy all collection // into a fixed size array, otherwise iterator will be invalidated Node[] shapes = shapeCollection.toArray(); for (Node node : shapes) { Shape shape = (Shape) node; // Filter out all shapes that we don't need if (shape.getShapeType() == ShapeType.TEXT_BOX) { // Create a new shape that will replace the existing shape Shape image = new Shape(doc, ShapeType.IMAGE); // Load the image into the new shape image.getImageData().setImage(getImageDir() + "Windows MetaFile.wmf"); // Make new shape's position to match the old shape image.setLeft(shape.getLeft()); image.setTop(shape.getTop()); image.setWidth(shape.getWidth()); image.setHeight(shape.getHeight()); image.setRelativeHorizontalPosition(shape.getRelativeHorizontalPosition()); image.setRelativeVerticalPosition(shape.getRelativeVerticalPosition()); image.setHorizontalAlignment(shape.getHorizontalAlignment()); image.setVerticalAlignment(shape.getVerticalAlignment()); image.setWrapType(shape.getWrapType()); image.setWrapSide(shape.getWrapSide()); // Insert new shape after the old shape and remove the old shape shape.getParentNode().insertAfter(image, shape); shape.remove(); } } doc.save(getArtifactsDir() + "Shape.ReplaceTextboxesWithImages.doc");
insertBefore | → inherited from CompositeNode |
public Node insertBefore(Node newChild, Node refChild) |
If refChild is null, inserts newChild at the end of the list of child nodes.
If the newChild is already in the tree, it is first removed.
If the node being inserted was created from another document, you should use
newChild
- The Node to insert.refChild
- The Node that is the reference node. The newChild is placed before this node.Example:
Shows how to add, update and delete child nodes from within a CompositeNode.Document doc = new Document(); // An empty document has one paragraph by default Assert.assertEquals(doc.getFirstSection().getBody().getParagraphs().getCount(), 1); // A paragraph is a composite node because it can contain runs, which are another type of node Paragraph paragraph = doc.getFirstSection().getBody().getFirstParagraph(); Run paragraphText = new Run(doc, "Initial text. "); paragraph.appendChild(paragraphText); // We will place these 3 children into the main text of our paragraph Run run1 = new Run(doc, "Run 1. "); Run run2 = new Run(doc, "Run 2. "); Run run3 = new Run(doc, "Run 3. "); // We initialized them but not in our paragraph yet Assert.assertEquals(paragraph.getText(), "Initial text. " + (char) 12); // Insert run2 before initial paragraph text. This will be at the start of the paragraph paragraph.insertBefore(run2, paragraphText); // Insert run3 after initial paragraph text. This will be at the end of the paragraph paragraph.insertAfter(run3, paragraphText); // Insert run1 before every other child node. run2 was the start of the paragraph, now it will be run1 paragraph.prependChild(run1); Assert.assertEquals(paragraph.getText(), "Run 1. Run 2. Initial text. Run 3. " + (char) 12); Assert.assertEquals(paragraph.getChildNodes(NodeType.ANY, true).getCount(), 4); // Access the child node collection and update/delete children ((Run) paragraph.getChildNodes(NodeType.RUN, true).get(1)).setText("Updated run 2. "); paragraph.getChildNodes(NodeType.RUN, true).remove(paragraphText); Assert.assertEquals(paragraph.getText(), "Run 1. Updated run 2. Run 3. " + (char) 12); Assert.assertEquals(paragraph.getChildNodes(NodeType.ANY, true).getCount(), 3);
iterator | → inherited from CompositeNode |
public java.util.Iterator<Node> iterator() |
Example:
Shows how to enumerate immediate children of a CompositeNode using the enumerator provided by the ChildNodes collection.NodeCollection children = paragraph.getChildNodes(); for (Node child : (Iterable<Node>) children) { // Paragraph may contain children of various types such as runs, shapes and so on if (child.getNodeType() == NodeType.RUN) { // Say we found the node that we want, do something useful Run run = (Run) child; System.out.println(run.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; } Assert.assertEquals(1, doc.getChildNodes(NodeType.SHAPE, true).getCount()); doc.save(getArtifactsDir() + "Image.DeleteAllImagesPreOrder.docx");
prependChild | → inherited from CompositeNode |
public Node prependChild(Node newChild) |
If the newChild is already in the tree, it is first removed.
If the node being inserted was created from another document, you should use
newChild
- The node to add.Example:
Shows how to add, update and delete child nodes from within a CompositeNode.Document doc = new Document(); // An empty document has one paragraph by default Assert.assertEquals(doc.getFirstSection().getBody().getParagraphs().getCount(), 1); // A paragraph is a composite node because it can contain runs, which are another type of node Paragraph paragraph = doc.getFirstSection().getBody().getFirstParagraph(); Run paragraphText = new Run(doc, "Initial text. "); paragraph.appendChild(paragraphText); // We will place these 3 children into the main text of our paragraph Run run1 = new Run(doc, "Run 1. "); Run run2 = new Run(doc, "Run 2. "); Run run3 = new Run(doc, "Run 3. "); // We initialized them but not in our paragraph yet Assert.assertEquals(paragraph.getText(), "Initial text. " + (char) 12); // Insert run2 before initial paragraph text. This will be at the start of the paragraph paragraph.insertBefore(run2, paragraphText); // Insert run3 after initial paragraph text. This will be at the end of the paragraph paragraph.insertAfter(run3, paragraphText); // Insert run1 before every other child node. run2 was the start of the paragraph, now it will be run1 paragraph.prependChild(run1); Assert.assertEquals(paragraph.getText(), "Run 1. Run 2. Initial text. Run 3. " + (char) 12); Assert.assertEquals(paragraph.getChildNodes(NodeType.ANY, true).getCount(), 4); // Access the child node collection and update/delete children ((Run) paragraph.getChildNodes(NodeType.RUN, true).get(1)).setText("Updated run 2. "); paragraph.getChildNodes(NodeType.RUN, true).remove(paragraphText); Assert.assertEquals(paragraph.getText(), "Run 1. Updated run 2. Run 3. " + (char) 12); Assert.assertEquals(paragraph.getChildNodes(NodeType.ANY, true).getCount(), 3);
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; } Assert.assertEquals(1, doc.getChildNodes(NodeType.SHAPE, true).getCount()); doc.save(getArtifactsDir() + "Image.DeleteAllImagesPreOrder.docx");
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(); } Assert.assertEquals(1, doc.getChildNodes(NodeType.SHAPE, true).getCount()); doc.save(getArtifactsDir() + "Image.DeleteAllImages.docx");
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; }
removeAllChildren | → inherited from CompositeNode |
public void removeAllChildren() |
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");
removeChild | → inherited from CompositeNode |
public Node removeChild(Node oldChild) |
The parent of oldChild is set to null after the node is removed.
oldChild
- The node to remove.Example:
Shows how to 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); }
removeSmartTags | → inherited from CompositeNode |
public void removeSmartTags() |
Example:
Removes all smart tags from descendant nodes of the composite node.Document doc = new Document(getMyDir() + "Document.docx"); // Remove smart tags from the first paragraph in the document doc.getFirstSection().getBody().getFirstParagraph().removeSmartTags();
selectNodes | → inherited from CompositeNode |
public NodeList selectNodes(java.lang.String xpath) |
Only expressions with element names are supported at the moment. Expressions that use attribute names are not supported.
xpath
- The XPath expression.Example:
Shows how to select certain nodes by using an XPath expression.Document doc = new Document(getMyDir() + "Tables.docx"); // This expression will extract all paragraph nodes which are descendants of any table node in the document // This will return any paragraphs which are in a table NodeList nodeList = doc.selectNodes("//Table//Paragraph"); // Iterate through the list with an enumerator and print the contents of every paragraph in each cell of the table int index = 0; Iterator<Node> e = nodeList.iterator(); while (e.hasNext()) { Node currentNode = e.next(); System.out.println(MessageFormat.format("Table paragraph index {0}, contents: \"{1}\"", index++, currentNode.getText().trim())); } // This expression will select any paragraphs that are direct children of any body node in the document nodeList = doc.selectNodes("//Body/Paragraph"); // We can treat the list as an array too Assert.assertEquals(nodeList.toArray().length, 4); // Use SelectSingleNode to select the first result of the same expression as above Node node = doc.selectSingleNode("//Body/Paragraph");
Example:
Shows how to test if a node is inside a field by using an XPath expression.// Let's pick a document we know has some fields in Document doc = new Document(getMyDir() + "Mail merge destination - Northwind employees.docx"); // Let's say we want to check if the Run below is inside a field Run run = (Run) doc.getChild(NodeType.RUN, 5, true); // Evaluate the XPath expression. The resulting NodeList will contain all nodes found inside a field a field (between FieldStart // and FieldEnd exclusive). There can however be FieldStart and FieldEnd nodes in the list if there are nested fields // in the path. Currently does not find rare fields in which the FieldCode or FieldResult spans across multiple paragraphs NodeList resultList = doc.selectNodes("//FieldStart/following-sibling::node()[following-sibling::FieldEnd]"); // Check if the specified run is one of the nodes that are inside the field for (Node node : (Iterable<Node>) resultList) { if (node == run) { System.out.println("The node is found inside a field"); break; } }
selectSingleNode | → inherited from CompositeNode |
public Node selectSingleNode(java.lang.String xpath) |
Only expressions with element names are supported at the moment. Expressions that use attribute names are not supported.
xpath
- The XPath expression.Example:
Shows how to select certain nodes by using an XPath expression.Document doc = new Document(getMyDir() + "Tables.docx"); // This expression will extract all paragraph nodes which are descendants of any table node in the document // This will return any paragraphs which are in a table NodeList nodeList = doc.selectNodes("//Table//Paragraph"); // Iterate through the list with an enumerator and print the contents of every paragraph in each cell of the table int index = 0; Iterator<Node> e = nodeList.iterator(); while (e.hasNext()) { Node currentNode = e.next(); System.out.println(MessageFormat.format("Table paragraph index {0}, contents: \"{1}\"", index++, currentNode.getText().trim())); } // This expression will select any paragraphs that are direct children of any body node in the document nodeList = doc.selectNodes("//Body/Paragraph"); // We can treat the list as an array too Assert.assertEquals(nodeList.toArray().length, 4); // Use SelectSingleNode to select the first result of the same expression as above Node node = doc.selectSingleNode("//Body/Paragraph");
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 using custom specified options.Document doc = new Document(getMyDir() + "Document.docx"); // 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 | → 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("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:
Exports the content of a node to String in HTML format using default options.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 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);
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));