Java TreeWalker.nextNode方法代码示例

import org.w3c.dom.traversal.TreeWalker; //导入方法依赖的package包/类
public Element getElementById(String elementId)
{
  Element element = xmljGetElementById(elementId);
  if (element == null)
    {
      TreeWalker walker = createTreeWalker(this, NodeFilter.SHOW_ELEMENT,
                                           null, false);
      for (Node node = walker.nextNode(); node != null;
           node = walker.nextNode())
        {
          GnomeElement e = (GnomeElement) node;
          if (e.userIdAttrs != null)
            {
              for (Iterator i = e.userIdAttrs.iterator(); i.hasNext(); )
                {
                  Attr attr = (Attr) i.next();
                  if (attr.getNodeValue().equals(elementId))
                    {
                      return e;
                    }
                }
            }
        }
    }
  return element;
}
 

import org.w3c.dom.traversal.TreeWalker; //导入方法依赖的package包/类
private void dropInitialAlef(Document doc) throws DOMException {
TreeWalker tw = ((DocumentTraversal) doc).createTreeWalker(doc, NodeFilter.SHOW_ELEMENT, new NameNodeFilter(MaryXML.TOKEN),
							   false);
Element m = null;
boolean prevEndsWithVowel = false;
while ((m = (Element) tw.nextNode()) != null) {
    System.out.println("Element: "+m.getTagName());
    if (m != null && m.getTagName().equals(MaryXML.TOKEN)) {
	String transcription = m.getAttribute("ph");
	System.out.println("transcription: "+transcription+", prevEndsWithVowel: "+prevEndsWithVowel);
	if ( transcription.startsWith("' a ") && prevEndsWithVowel ) {
	    System.out.println("Removing A");
	    m.setAttribute("ph", transcription.replaceAll("^' a -?","' "));
	}
	if ( transcription.matches(".*[AUIaui][01]?$") ) {
	    prevEndsWithVowel = true;
	}
	
    }
}
   }
 

import org.w3c.dom.traversal.TreeWalker; //导入方法依赖的package包/类
protected void vocaliseDoc(Document doc) throws Exception {
TreeWalker tw = ((DocumentTraversal) doc).createTreeWalker(doc, NodeFilter.SHOW_ELEMENT,
							   new NameNodeFilter(MaryXML.TOKEN), false);
Element t = null;
       StringBuilder origText = new StringBuilder();
while ((t = (Element) tw.nextNode()) != null) {
    //if (MaryDomUtils.hasAncestor(t, MaryXML.SAYAS) || t.hasAttribute("ph") || t.hasAttribute("sounds_like")) {
	// ignore token
    //continue;
    origText.append(" " + MaryDomUtils.tokenText(t));
}
String vocText = vocaliseText(origText.toString());

String[] vocTextList = vocText.split(" ");


TreeWalker tw2 = ((DocumentTraversal) doc).createTreeWalker(doc, NodeFilter.SHOW_ELEMENT,
							    new NameNodeFilter(MaryXML.TOKEN), false);
Element t2 = null;
int i = 0;

while ((t2 = (Element) tw2.nextNode()) != null && i < vocTextList.length) {
    MaryDomUtils.setTokenText(t2, vocTextList[i]);
    i++;
}
   }
 

import org.w3c.dom.traversal.TreeWalker; //导入方法依赖的package包/类
@Test
   public void canProcessPunctuatedArabicToTokens() throws Exception {
   	// setup
   	MaryInterface mary = new LocalMaryInterface();
   	mary.setInputType(MaryDataType.TEXT.name());
   	mary.setOutputType(MaryDataType.TOKENS.name());
   	mary.setLocale(new Locale("ar"));

   	String example = "مدينة شِبام الأثريَّة التاريخيَّة، إحدى أقدم مُدن";


   	// exercise
   	Document doc = mary.generateXML(example);
   	// verify
   	assertNotNull(doc);

//We should get 8 tokens from this example, 7 words and one comma
TreeWalker tw = ((DocumentTraversal) doc).createTreeWalker(doc, NodeFilter.SHOW_ELEMENT,
							   new NameNodeFilter(MaryXML.TOKEN), false);
Element t = null;
int count = 0;
while ((t = (Element) tw.nextNode()) != null) {
    count++;
}
assertEquals(8, count);


   }
 

import org.w3c.dom.traversal.TreeWalker; //导入方法依赖的package包/类
/**
 * Get the last descendant element with the given tag name, or <code>null</code> if there is no such element.
 * 
 * @param e
 *            e
 * @param name
 *            name
 * @return previous
 */
public static Element getLastElementByTagName(Element e, String name) {
	// This implementation is certainly inefficient, but I have
	// no better idea at the moment.
	TreeWalker tw = ((DocumentTraversal) e.getOwnerDocument()).createTreeWalker(e, NodeFilter.SHOW_ELEMENT,
			new NameNodeFilter(name), true);
	Node current = null;
	Node previous = null;
	while ((current = tw.nextNode()) != null)
		previous = current;
	return (Element) previous;
}
 

import org.w3c.dom.traversal.TreeWalker; //导入方法依赖的package包/类
public static boolean isLastOfItsKindIn(Node node, Node ancestor) {
	if (node == null || ancestor == null)
		return false;
	Document doc = node.getOwnerDocument();
	if (doc == null)
		return false;
	TreeWalker tw = ((DocumentTraversal) doc).createTreeWalker(doc, NodeFilter.SHOW_ALL,
			new NameNodeFilter(node.getNodeName()), true);
	tw.setCurrentNode(node);
	Node next = tw.nextNode();

	return next == null || // no node with same name after this one
			!isAncestor(ancestor, next); // next is not in the same ancestor
}
 

import org.w3c.dom.traversal.TreeWalker; //导入方法依赖的package包/类
/**
 * Find the Element with the same tag name as <code>element</code> following <code>element</code> within the same subtree
 * under <code>root</code>. Precondition: <code>root</code> must be an ancestor of <code>element</code>.
 * 
 * @param element
 *            element
 * @param root
 *            root
 * @return that Element, or <code>null</code> if there is no such Element.
 */
public static Element getNextOfItsKindIn(Element element, Element root) {
	if (element == null || root == null)
		return null;
	String tagname = element.getTagName();
	TreeWalker tw = ((DocumentTraversal) element.getOwnerDocument()).createTreeWalker(root, NodeFilter.SHOW_ELEMENT,
			new NameNodeFilter(tagname), true);
	tw.setCurrentNode(element);
	for (Node next = tw.nextNode(); next != null; next = tw.nextNode()) {
		if (next.getNodeName().equals(tagname)) {
			return (Element) next;
		}
	}
	return null;
}
 

import org.w3c.dom.traversal.TreeWalker; //导入方法依赖的package包/类
public ElementMap(Document doc) {
	elementIDs = new HashMap<String, Element>();
	elementNames = new HashMap<String, Element>();
       DocumentTraversal traversal = (DocumentTraversal) doc;
       TreeWalker w = traversal.createTreeWalker(doc, NodeFilter.SHOW_ELEMENT, null, false);
	//TreeWalker w = new TidyTreeWalker(doc, NodeFilter.SHOW_ELEMENT);
	Element current;
	while ((current = (Element) w.nextNode()) != null) {
		elementNames.put(current.getNodeName().toLowerCase(), current);
		String id = current.getAttribute("id");
		if(id!=null)
			elementIDs.put(id, current);
	}
}
 

import org.w3c.dom.traversal.TreeWalker; //导入方法依赖的package包/类
/**
 * Get the first child element with the given tag name, or <code>null</code> if there is no such element.
 * 
 * @param n
 *            n
 * @param name
 *            name
 * @return tx.nextNode
 */
public static Element getFirstElementByTagName(Node n, String name) {
	Document doc = (n instanceof Document) ? (Document) n : n.getOwnerDocument();
	TreeWalker tw = ((DocumentTraversal) doc).createTreeWalker(n, NodeFilter.SHOW_ELEMENT, new NameNodeFilter(name), true);
	return (Element) tw.nextNode();
}