Examples with DocumentType org.w3c.dom.DocumentType used on opensource projects

Example 41 with DocumentType

use of org.w3c.dom.DocumentType in project nokogiri by sparklemotion.

the class XmlDtd method newEmpty.

public static XmlDtd newEmpty(Ruby runtime, Document doc, IRubyObject name, IRubyObject external_id, IRubyObject system_id) {
    DocumentType placeholder;
    if (doc.getDoctype() == null) {
        String javaName = NokogiriHelpers.rubyStringToString(name);
        String javaExternalId = NokogiriHelpers.rubyStringToString(external_id);
        String javaSystemId = NokogiriHelpers.rubyStringToString(system_id);
        placeholder = doc.getImplementation().createDocumentType(javaName, javaExternalId, javaSystemId);
        doc.appendChild(placeholder);
    } else {
        placeholder = doc.getDoctype();
    }
    // FIXME: what if the document had a doc type, why are we here ?
    XmlDtd dtd = (XmlDtd) NokogiriService.XML_DTD_ALLOCATOR.allocate(runtime, getNokogiriClass(runtime, "Nokogiri::XML::DTD"));
    dtd.setNode(runtime, placeholder);
    dtd.name = name;
    dtd.pubId = external_id;
    dtd.sysId = system_id;
    return dtd;
}

Example 42 with DocumentType

use of org.w3c.dom.DocumentType in project nokogiri by sparklemotion.

the class XmlDtd method accept.

@Override
public void accept(ThreadContext context, SaveContextVisitor visitor) {
    // since we use nekoDTD to parse dtd, node might be ElementImpl type
    // An external subset doesn't need to show up, so this method just see docType.
    DocumentType docType = node.getOwnerDocument().getDoctype();
    visitor.enter(docType);
    visitor.leave(docType);
}

Example 43 with DocumentType

use of org.w3c.dom.DocumentType in project nokogiri by sparklemotion.

the class DOM2DTM method getUnparsedEntityURI.

/**
 * 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;
}

Example 44 with DocumentType

use of org.w3c.dom.DocumentType in project generator by mybatis.

the class XmlFileMergerJaxp method getMergedSource.

public static String getMergedSource(InputSource newFile, InputSource existingFile, String existingFileName) throws IOException, SAXException, ParserConfigurationException, ShellException {
    DocumentBuilderFactory factory = DocumentBuilderFactory.newInstance();
    factory.setAttribute(XMLConstants.ACCESS_EXTERNAL_DTD, "");
    factory.setAttribute(XMLConstants.ACCESS_EXTERNAL_SCHEMA, "");
    factory.setExpandEntityReferences(false);
    factory.setFeature(XMLConstants.FEATURE_SECURE_PROCESSING, true);
    DocumentBuilder builder = factory.newDocumentBuilder();
    builder.setEntityResolver(new NullEntityResolver());
    Document existingDocument = builder.parse(existingFile);
    Document newDocument = builder.parse(newFile);
    DocumentType newDocType = newDocument.getDoctype();
    DocumentType existingDocType = existingDocument.getDoctype();
    if (!newDocType.getName().equals(existingDocType.getName())) {
        throw new ShellException(getString(// $NON-NLS-1$
        "Warning.12", existingFileName));
    }
    Element existingRootElement = existingDocument.getDocumentElement();
    Element newRootElement = newDocument.getDocumentElement();
    // reconcile the root element attributes -
    // take all attributes from the new element and add to the existing
    // element
    // remove all attributes from the existing root element
    NamedNodeMap attributes = existingRootElement.getAttributes();
    int attributeCount = attributes.getLength();
    for (int i = attributeCount - 1; i >= 0; i--) {
        Node node = attributes.item(i);
        existingRootElement.removeAttribute(node.getNodeName());
    }
    // add attributes from the new root node to the old root node
    attributes = newRootElement.getAttributes();
    attributeCount = attributes.getLength();
    for (int i = 0; i < attributeCount; i++) {
        Node node = attributes.item(i);
        existingRootElement.setAttribute(node.getNodeName(), node.getNodeValue());
    }
    // remove the old generated elements and any
    // white space before the old nodes
    List<Node> nodesToDelete = new ArrayList<>();
    NodeList children = existingRootElement.getChildNodes();
    int length = children.getLength();
    for (int i = 0; i < length; i++) {
        Node node = children.item(i);
        if (isGeneratedNode(node)) {
            nodesToDelete.add(node);
        } else if (isWhiteSpace(node) && isGeneratedNode(children.item(i + 1))) {
            nodesToDelete.add(node);
        }
    }
    for (Node node : nodesToDelete) {
        existingRootElement.removeChild(node);
    }
    // add the new generated elements
    children = newRootElement.getChildNodes();
    length = children.getLength();
    Node firstChild = existingRootElement.getFirstChild();
    for (int i = 0; i < length; i++) {
        Node node = children.item(i);
        // don't add the last node if it is only white space
        if (i == length - 1 && isWhiteSpace(node)) {
            break;
        }
        Node newNode = existingDocument.importNode(node, true);
        if (firstChild == null) {
            existingRootElement.appendChild(newNode);
        } else {
            existingRootElement.insertBefore(newNode, firstChild);
        }
    }
    // pretty print the result
    return prettyPrint(existingDocument);
}

Example 45 with DocumentType

use of org.w3c.dom.DocumentType in project jsoup by jhy.

the class W3CDomTest method convertsGoogle.

@Test
public void convertsGoogle() throws IOException {
    File in = ParseTest.getFile("/htmltests/google-ipod.html.gz");
    org.jsoup.nodes.Document doc = Jsoup.parse(in, "UTF8");
    W3CDom w3c = new W3CDom();
    Document wDoc = w3c.fromJsoup(doc);
    Node htmlEl = wDoc.getChildNodes().item(1);
    assertNull(htmlEl.getNamespaceURI());
    assertEquals("html", htmlEl.getLocalName());
    assertEquals("html", htmlEl.getNodeName());
    DocumentType doctype = wDoc.getDoctype();
    Node doctypeNode = wDoc.getChildNodes().item(0);
    assertSame(doctype, doctypeNode);
    assertEquals("html", doctype.getName());
    String xml = W3CDom.asString(wDoc, W3CDom.OutputXml());
    assertTrue(xml.contains("ipod"));
    Document roundTrip = parseXml(xml, true);
    assertEquals("Images", roundTrip.getElementsByTagName("a").item(0).getTextContent());
}