dom2dtm.java

来自「java1.6众多例子参考」· Java 代码 · 共 1,764 行 · 第 1/4 页

  /**
   * Returns the <code>Element</code> whose <code>ID</code> is given by
   * <code>elementId</code>. If no such element exists, returns
   * <code>DTM.NULL</code>. Behavior is not defined if more than one element
   * has this <code>ID</code>. Attributes (including those
   * with the name "ID") are not of type ID unless so defined by DTD/Schema
   * information available to the DTM implementation.
   * Implementations that do not know whether attributes are of type ID or
   * not are expected to return <code>DTM.NULL</code>.
   *
   * <p>%REVIEW% Presumably IDs are still scoped to a single document,
   * and this operation searches only within a single document, right?
   * Wouldn't want collisions between DTMs in the same process.</p>
   *
   * @param elementId The unique <code>id</code> value for an element.
   * @return The handle of the matching element.
   */
  public int getElementById(String elementId)
  {

    Document doc = (m_root.getNodeType() == Node.DOCUMENT_NODE) 
        ? (Document) m_root : m_root.getOwnerDocument();
        
    if(null != doc)
    {
      Node elem = doc.getElementById(elementId);
      if(null != elem)
      {
        int elemHandle = getHandleFromNode(elem);
        
        if(DTM.NULL == elemHandle)
        {
          int identity = m_nodes.size()-1;
          while (DTM.NULL != (identity = getNextNodeIdentity(identity)))
          {
            Node node = getNode(identity);
            if(node == elem)
            {
              elemHandle = getHandleFromNode(elem);
              break;
            }
           }
        }
        
        return elemHandle;
      }
    
    }
    return DTM.NULL;
  }

  /**
   * The getUnparsedEntityURI function returns the URI of the unparsed
   * entity with the specified name in the same document as the context
   * node (see [3.3 Unparsed Entities]). It returns the empty string if
   * there is no such entity.
   * <p>
   * XML processors may choose to use the System Identifier (if one
   * is provided) to resolve the entity, rather than the URI in the
   * Public Identifier. The details are dependent on the processor, and
   * we would have to support some form of plug-in resolver to handle
   * this properly. Currently, we simply return the System Identifier if
   * present, and hope that it a usable URI or that our caller can
   * map it to one.
   * TODO: Resolve Public Identifiers... or consider changing function name.
   * <p>
   * If we find a relative URI
   * reference, XML expects it to be resolved in terms of the base URI
   * of the document. The DOM doesn't do that for us, and it isn't
   * entirely clear whether that should be done here; currently that's
   * pushed up to a higher level of our application. (Note that DOM Level
   * 1 didn't store the document's base URI.)
   * TODO: Consider resolving Relative URIs.
   * <p>
   * (The DOM's statement that "An XML processor may choose to
   * completely expand entities before the structure model is passed
   * to the DOM" refers only to parsed entities, not unparsed, and hence
   * doesn't affect this function.)
   *
   * @param name A string containing the Entity Name of the unparsed
   * entity.
   *
   * @return String containing the URI of the Unparsed Entity, or an
   * empty string if no such entity exists.
   */
  public String getUnparsedEntityURI(String name)
  {

    String url = "";
    Document doc = (m_root.getNodeType() == Node.DOCUMENT_NODE) 
        ? (Document) m_root : m_root.getOwnerDocument();

    if (null != doc)
    {
      DocumentType doctype = doc.getDoctype();
  
      if (null != doctype)
      {
        NamedNodeMap entities = doctype.getEntities();
        if(null == entities)
          return url;
        Entity entity = (Entity) entities.getNamedItem(name);
        if(null == entity)
          return url;
        
        String notationName = entity.getNotationName();
  
        if (null != notationName)  // then it's unparsed
        {
          // The draft says: "The XSLT processor may use the public 
          // identifier to generate a URI for the entity instead of the URI 
          // specified in the system identifier. If the XSLT processor does 
          // not use the public identifier to generate the URI, it must use 
          // the system identifier; if the system identifier is a relative 
          // URI, it must be resolved into an absolute URI using the URI of 
          // the resource containing the entity declaration as the base 
          // URI [RFC2396]."
          // So I'm falling a bit short here.
          url = entity.getSystemId();
  
          if (null == url)
          {
            url = entity.getPublicId();
          }
          else
          {
            // This should be resolved to an absolute URL, but that's hard 
            // to do from here.
          }        
        }
      }
    }

    return url;
  }

  /**
   *     5. [specified] A flag indicating whether this attribute was actually
   *        specified in the start-tag of its element, or was defaulted from the
   *        DTD.
   *
   * @param attributeHandle the attribute handle
   * @return <code>true</code> if the attribute was specified;
   *         <code>false</code> if it was defaulted.
   */
  public boolean isAttributeSpecified(int attributeHandle)
  {
    int type = getNodeType(attributeHandle);

    if (DTM.ATTRIBUTE_NODE == type)
    {
      Attr attr = (Attr)getNode(attributeHandle);
      return attr.getSpecified();
    }
    return false;
  }

  /** Bind an IncrementalSAXSource to this DTM. NOT RELEVANT for DOM2DTM, since
   * we're wrapped around an existing DOM.
   *
   * @param source The IncrementalSAXSource that we want to recieve events from
   * on demand.
   */
  public void setIncrementalSAXSource(IncrementalSAXSource source)
  {
  }
  
  /** getContentHandler returns "our SAX builder" -- the thing that
   * someone else should send SAX events to in order to extend this
   * DTM model.
   *
   * @return null if this model doesn't respond to SAX events,
   * "this" if the DTM object has a built-in SAX ContentHandler,
   * the IncrmentalSAXSource if we're bound to one and should receive
   * the SAX stream via it for incremental build purposes...
   * */
  public org.xml.sax.ContentHandler getContentHandler()
  {
      return null;
  }
  
  /**
   * Return this DTM's lexical handler.
   *
   * %REVIEW% Should this return null if constrution already done/begun?
   *
   * @return null if this model doesn't respond to lexical SAX events,
   * "this" if the DTM object has a built-in SAX ContentHandler,
   * the IncrementalSAXSource if we're bound to one and should receive
   * the SAX stream via it for incremental build purposes...
   */
  public org.xml.sax.ext.LexicalHandler getLexicalHandler()
  {

    return null;
  }

  
  /**
   * Return this DTM's EntityResolver.
   *
   * @return null if this model doesn't respond to SAX entity ref events.
   */
  public org.xml.sax.EntityResolver getEntityResolver()
  {

    return null;
  }
  
  /**
   * Return this DTM's DTDHandler.
   *
   * @return null if this model doesn't respond to SAX dtd events.
   */
  public org.xml.sax.DTDHandler getDTDHandler()
  {

    return null;
  }

  /**
   * Return this DTM's ErrorHandler.
   *
   * @return null if this model doesn't respond to SAX error events.
   */
  public org.xml.sax.ErrorHandler getErrorHandler()
  {

    return null;
  }
  
  /**
   * Return this DTM's DeclHandler.
   *
   * @return null if this model doesn't respond to SAX Decl events.
   */
  public org.xml.sax.ext.DeclHandler getDeclHandler()
  {

    return null;
  }  

  /** @return true iff we're building this model incrementally (eg
   * we're partnered with a IncrementalSAXSource) and thus require that the
   * transformation and the parse run simultaneously. Guidance to the
   * DTMManager.
   * */
  public boolean needsTwoThreads()
  {
    return false;
  }

  // ========== Direct SAX Dispatch, for optimization purposes ========
  
  /**
   * Returns whether the specified <var>ch</var> conforms to the XML 1.0 definition
   * of whitespace.  Refer to <A href="http://www.w3.org/TR/1998/REC-xml-19980210#NT-S">
   * the definition of <CODE>S</CODE></A> for details.
   * @param   ch      Character to check as XML whitespace.
   * @return          =true if <var>ch</var> is XML whitespace; otherwise =false.
   */
  private static boolean isSpace(char ch)
  {
    return XMLCharacterRecognizer.isWhiteSpace(ch);  // Take the easy way out for now.
  }

  /**
   * Directly call the
   * characters method on the passed ContentHandler for the
   * string-value of the given node (see http://www.w3.org/TR/xpath#data-model
   * for the definition of a node's string-value). Multiple calls to the
   * ContentHandler's characters methods may well occur for a single call to
   * this method.
   *
   * @param nodeHandle The node ID.
   * @param ch A non-null reference to a ContentHandler.
   *
   * @throws org.xml.sax.SAXException
   */
  public void dispatchCharactersEvents(
          int nodeHandle, org.xml.sax.ContentHandler ch, 
          boolean normalize)
            throws org.xml.sax.SAXException
  {
    if(normalize)
    {
      XMLString str = getStringValue(nodeHandle);
      str = str.fixWhiteSpace(true, true, false);
      str.dispatchCharactersEvents(ch);
    }
    else
    {
      int type = getNodeType(nodeHandle);
      Node node = getNode(nodeHandle);
      dispatchNodeData(node, ch, 0);
          // Text coalition -- a DTM text node may represent multiple
          // DOM nodes.
          if(TEXT_NODE == type || CDATA_SECTION_NODE == type)
          {
                  while( null != (node=logicalNextDOMTextNode(node)) )
                  {
                      dispatchNodeData(node, ch, 0);
                  }
          }
    }
  }
  
  /**
   * Retrieve the text content of a DOM subtree, appending it into a
   * user-supplied FastStringBuffer object. Note that attributes are
   * not considered part of the content of an element.
   * <p>
   * There are open questions regarding whitespace stripping. 
   * Currently we make no special effort in that regard, since the standard
   * DOM doesn't yet provide DTD-based information to distinguish
   * whitespace-in-element-context from genuine #PCDATA. Note that we
   * should probably also consider xml:space if/when we address this.
   * DOM Level 3 may solve the problem for us.
   * <p>
   * %REVIEW% Note that as a DOM-level operation, it can be argued that this
   * routine _shouldn't_ perform any processing beyond what the DOM already
   * does, and that whitespace stripping and so on belong at the DTM level.
   * If you want a stripped DOM view, wrap DTM2DOM around DOM2DTM.
   *
   * @param node Node whose subtree is to be walked, gathering the
   * contents of all Text or CDATASection nodes.
   */
  protected static void dispatchNodeData(Node node, 
                                         org.xml.sax.ContentHandler ch, 
                                         int depth)
            throws org.xml.sax.SAXException
  {

    switch (node.getNodeType())
    {
    case Node.DOCUMENT_FRAGMENT_NODE :
    case Node.DOCUMENT_NODE :
    case Node.ELEMENT_NODE :
    {
      for (Node child = node.getFirstChild(); null != child;
              child = child.getNextSibling())
      {
        dispatchNodeData(child, ch, depth+1);
      }
    }
    break;
    case Node.PROCESSING_INSTRUCTION_NODE : // %REVIEW%
    case Node.COMMENT_NODE :
      if(0 != depth)
        break;
        // NOTE: Because this operation works in the DOM space, it does _not_ attempt
        // to perform Text Coalition. That should only be done in DTM space. 
    case Node.TEXT_NODE :
    case Node.CDATA_SECTION_NODE :
    case Node.ATTRIBUTE_NODE :
      String str = node.getNodeValue();
      if(ch instanceof CharacterNodeHandler)
      {
        ((CharacterNodeHandler)ch).characters(node);
      }
      else
      {
        ch.characters(str.toCharArray(), 0, str.length());
      }
      break;
//    /* case Node.PROCESSING_INSTRUCTION_NODE :
//      // warning(XPATHErrorResources.WG_PARSING_AND_PREPARING);        
//      break; */
    default :
      // ignore
      break;
    }
  }
  
  TreeWalker m_walker = new TreeWalker(null);
  
  /**
   * Directly create SAX parser events from a subtree.
   *
   * @param nodeHandle The node ID.
   * @param ch A non-null reference to a ContentHandler.
   *
   * @throws org.xml.sax.SAXException
   */
  public void dispatchToEvents(int nodeHandle, org.xml.sax.ContentHandler ch)
          throws org.xml.sax.SAXException
  {
    TreeWalker treeWalker = m_walker;
    ContentHandler prevCH = treeWalker.getContentHandler();
    
    if(null != prevCH)
    {
      treeWalker = new TreeWalker(null);
    }
    treeWalker.setContentHandler(ch);
    
    try
    {
      Node node = getNode(nodeHandle);
      treeWalker.traverse(node);
    }
    finally
    {
      treeWalker.setContentHandler(null);
    }
  }
  
  public interface CharacterNodeHandler
  {
    public void characters(Node node)
            throws org.xml.sax.SAXException;
  }

  /**
   * For the moment all the run time properties are ignored by this
   * class.
   *
   * @param property a <code>String</code> value
   * @param value an <code>Object</code> value
   */
  public void setProperty(String property, Object value)
  {
  }
  
  /**
   * No source information is available for DOM2DTM, so return
   * <code>null</code> here.
   *
   * @param node an <code>int</code> value
   * @return null
   */
  public SourceLocator getSourceLocatorFor(int node)
  {
    return null;
  }

}