Java Code Examples for org.w3c.dom.Document#getDoctype()

/**
 * Returns the document type public identifier
 * specified for this document, or null.
 */
public static String whichDoctypePublic( Document doc )
{
    DocumentType doctype;

       /*  DOM Level 2 was introduced into the code base*/
       doctype = doc.getDoctype();
       if ( doctype != null ) {
       // Note on catch: DOM Level 1 does not specify this method
       // and the code will throw a NoSuchMethodError
       try {
       return doctype.getPublicId();
       } catch ( Error except ) {  }
       }

    if ( doc instanceof HTMLDocument )
        return DTD.XHTMLPublicId;
    return null;
}
 

/**
 * Returns the document type public identifier
 * specified for this document, or null.
 */
public static String whichDoctypePublic( Document doc )
{
    DocumentType doctype;

       /*  DOM Level 2 was introduced into the code base*/
       doctype = doc.getDoctype();
       if ( doctype != null ) {
       // Note on catch: DOM Level 1 does not specify this method
       // and the code will throw a NoSuchMethodError
       try {
       return doctype.getPublicId();
       } catch ( Error except ) {  }
       }

    if ( doc instanceof HTMLDocument )
        return DTD.XHTMLPublicId;
    return null;
}
 

private String getPublicIdFromImpl(RootInterfaceImpl rootProxyImpl) {
    String result = null;

    GraphManager gm = rootProxyImpl.graphManager();
    if (gm != null) {
        Document d = gm.getXmlDocument();
        if (d != null) {
            DocumentType dt = d.getDoctype();
            if (dt != null) {
                result = dt.getPublicId();
            }
        }
    }

    return result;
}
 

/**
 * Returns the document type public identifier
 * specified for this document, or null.
 */
public static String whichDoctypePublic( Document doc )
{
    DocumentType doctype;

       /*  DOM Level 2 was introduced into the code base*/
       doctype = doc.getDoctype();
       if ( doctype != null ) {
       // Note on catch: DOM Level 1 does not specify this method
       // and the code will throw a NoSuchMethodError
       try {
       return doctype.getPublicId();
       } catch ( Error except ) {  }
       }

    if ( doc instanceof HTMLDocument )
        return DTD.XHTMLPublicId;
    return null;
}
 

/**
 * Returns the document type system identifier
 * specified for this document, or null.
 */
public static String whichDoctypeSystem( Document doc )
{
    DocumentType doctype;

    /* DOM Level 2 was introduced into the code base*/
       doctype = doc.getDoctype();
       if ( doctype != null ) {
       // Note on catch: DOM Level 1 does not specify this method
       // and the code will throw a NoSuchMethodError
       try {
       return doctype.getSystemId();
       } catch ( Error except ) { }
       }

    if ( doc instanceof HTMLDocument )
        return DTD.XHTMLSystemId;
    return null;
}
 

private OpenElementStack makeElementStack(Document doc, MessageQueue mq) {
  Namespaces ns = this.ns;
  DocumentType doctype = doc.getDoctype();
  if (doctype != null) {
    // If we have a DOCTYPE, use its SYSTEM ID to determine the default
    // namespace.
    String sysid = doctype.getSystemId();
    String nsUri = DoctypeMaker.systemIdToNsUri(sysid);
    if (nsUri != null) { ns = new Namespaces(ns, "", nsUri); }
  }
  return asXml
      ? OpenElementStack.Factory.createXmlElementStack(
          doc, needsDebugData, ns, mq)
      : OpenElementStack.Factory.createHtml5ElementStack(
          doc, needsDebugData, mq);
}
 

public static void write(Document doc, OutputStream out) throws IOException {
    // XXX note that this may fail to write out namespaces correctly if the document
    // is created with namespaces and no explicit prefixes; however no code in
    // this package is likely to be doing so
    try {
        Transformer t = TransformerFactory.newInstance().newTransformer(
                new StreamSource(new StringReader(IDENTITY_XSLT_WITH_INDENT)));
        DocumentType dt = doc.getDoctype();
        if (dt != null) {
            String pub = dt.getPublicId();
            if (pub != null) {
                t.setOutputProperty(OutputKeys.DOCTYPE_PUBLIC, pub);
            }
            t.setOutputProperty(OutputKeys.DOCTYPE_SYSTEM, dt.getSystemId());
        }
        t.setOutputProperty(OutputKeys.ENCODING, "UTF-8"); // NOI18N
        Source source = new DOMSource(doc);
        Result result = new StreamResult(out);
        t.transform(source, result);
    } catch (Exception | TransformerFactoryConfigurationError e) {
        throw new IOException(e);
    }
}
 

/**
 * Extracts NamedNodeMap of entities. We need this to validate
 * elements and attributes of type xs:ENTITY, xs:ENTITIES or
 * types dervied from them.
 */
private void setupEntityMap(Document doc) {
    if (doc != null) {
        DocumentType docType = doc.getDoctype();
        if (docType != null) {
            fEntities = docType.getEntities();
            return;
        }
    }
    fEntities = null;
}
 

private Document removeDocType(Document document) {
    if (document != null) {
        org.w3c.dom.Element docElement = document.getDocumentElement();
        if (docElement != null) {
            org.w3c.dom.DocumentType docType = document.getDoctype();
            if (docType != null) {
                document.removeChild(docType); //NOI18N
            }
        }
    }
    return document;
}
 

/**
 * Extracts NamedNodeMap of entities. We need this to validate
 * elements and attributes of type xs:ENTITY, xs:ENTITIES or
 * types dervied from them.
 */
private void setupEntityMap(Document doc) {
    if (doc != null) {
        DocumentType docType = doc.getDoctype();
        if (docType != null) {
            fEntities = docType.getEntities();
            return;
        }
    }
    fEntities = null;
}
 

/**
 * Extracts NamedNodeMap of entities. We need this to validate
 * elements and attributes of type xs:ENTITY, xs:ENTITIES or
 * types dervied from them.
 */
private void setupEntityMap(Document doc) {
    if (doc != null) {
        DocumentType docType = doc.getDoctype();
        if (docType != null) {
            fEntities = docType.getEntities();
            return;
        }
    }
    fEntities = null;
}
 

/**
 * Extracts NamedNodeMap of entities. We need this to validate
 * elements and attributes of type xs:ENTITY, xs:ENTITIES or
 * types dervied from them.
 */
private void setupEntityMap(Document doc) {
    if (doc != null) {
        DocumentType docType = doc.getDoctype();
        if (docType != null) {
            fEntities = docType.getEntities();
            return;
        }
    }
    fEntities = null;
}
 

protected cfData getXmlDocType() {
	Document doc = (Document) nodeData;
	if (doc.getDoctype() != null)
		return new cfXmlData(this, doc.getDoctype(), isCaseSensitive());
	else
		return null;
}
 

private Document removeDocType(Document document){
    if (document != null) {
        org.w3c.dom.Element docElement = document.getDocumentElement();
        if (docElement != null) {
            org.w3c.dom.DocumentType docType = document.getDoctype();
            if (docType != null) {
                document.removeChild(docType); //NOI18N
            }
        }
    }
    return document;
}
 

/**
 * Validates an XML resource against a list of DTD schemas or as indicated by a
 * DOCTYPE declaration. Validation errors are reported to the given handler. If
 * no DTD references are provided the external schema reference in the DOCTYPE
 * declaration is used (Note: an internal subset is ignored).
 * 
 * @param doc
 *            The input Document.
 * @param dtdList
 *            A list of DTD schema references. May be empty but not null.
 * @param errHandler
 *            An ErrorHandler that collects validation errors.
 * @throws Exception
 *             If any errors occur while attempting to validate the document.
 */
private void validateAgainstDTDList(Document doc, ArrayList<Object> dtdList,
		ErrorHandler errHandler) throws Exception {
	jlogger.finer("Validating XML resource from " + doc.getDocumentURI());
	DocumentBuilder db = dtdValidatingDBF.newDocumentBuilder();
	db.setErrorHandler(errHandler);
             // Fortify Mod: prevent external entity injection
         // includes try block to capture exceptions to setFeature.
	TransformerFactory tf = TransformerFactory.newInstance();
	try {
     	        tf.setFeature(XMLConstants.FEATURE_SECURE_PROCESSING, true);
	    } catch (Exception e) {
	        jlogger.warning("Failed to secure Transformer");
	    }
	// End Fortify Mod
     Transformer copier = tf.newTransformer();
          ByteArrayOutputStream content = new ByteArrayOutputStream();
	Result copy = new StreamResult(content);
	if (dtdList.isEmpty()) {
		DocumentType doctype = doc.getDoctype();
		if (null == doctype) {
			return;
		}
		URI systemId = URI.create(doctype.getSystemId());
		if (!systemId.isAbsolute() && null != doc.getBaseURI()) {
			systemId = URI.create(doc.getBaseURI()).resolve(systemId);
		}
		copier.setOutputProperty(OutputKeys.DOCTYPE_SYSTEM,
				systemId.toString());
		copier.transform(new DOMSource(doc), copy);
		db.parse(new ByteArrayInputStream(content.toByteArray()));
	} else {
		for (Object dtdRef : dtdList) {
			content.reset();
			copier.setOutputProperty(OutputKeys.DOCTYPE_SYSTEM,
					dtdRef.toString());
			copier.transform(new DOMSource(doc), copy);
			db.parse(new ByteArrayInputStream(content.toByteArray()));
		}
	}
}
 

/**
 * 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;
}
 

/**
 * 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 levelof 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.
 * @param doc Document node for the document to be searched.
 *
 * @return String containing the URI of the Unparsed Entity, or an
 * empty string if no such entity exists.
 */
public String getUnparsedEntityURI(String name, Document doc)
{

  String url = "";
  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;
}
 

/**
 * @param dom the W3C DOM XML document to read from 
 */
public MCRDOMContent(Document dom) {
    super();
    this.dom = dom;
    super.docType = dom.getDoctype() == null ? dom.getDocumentElement().getLocalName() : dom.getDoctype().getName();
}
 

/**
 * 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 levelof 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.
 * @param doc Document node for the document to be searched.
 *
 * @return String containing the URI of the Unparsed Entity, or an
 * empty string if no such entity exists.
 */
public String getUnparsedEntityURI(String name, Document doc)
{

  String url = "";
  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;
}
 

/**
 * 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 levelof 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.
 * @param doc Document node for the document to be searched.
 *
 * @return String containing the URI of the Unparsed Entity, or an
 * empty string if no such entity exists.
 */
public String getUnparsedEntityURI(String name, Document doc)
{

  String url = "";
  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;
}