Examples with DOMParser org.apache.xerces.parsers.DOMParser used on opensource projects

Example 11 with DOMParser

use of org.apache.xerces.parsers.DOMParser in project nutch by apache.

the class TestNodeWalker method testSkipChildren.

@Test
public void testSkipChildren() {
    DOMParser parser = new DOMParser();
    try {
        parser.setFeature("http://xml.org/sax/features/validation", false);
        parser.setFeature("http://apache.org/xml/features/nonvalidating/load-external-dtd", false);
        parser.parse(new InputSource(new ByteArrayInputStream(WEBPAGE.getBytes())));
    } catch (Exception e) {
        e.printStackTrace();
    }
    StringBuffer sb = new StringBuffer();
    NodeWalker walker = new NodeWalker(parser.getDocument());
    while (walker.hasNext()) {
        Node currentNode = walker.nextNode();
        short nodeType = currentNode.getNodeType();
        if (nodeType == Node.TEXT_NODE) {
            String text = currentNode.getNodeValue();
            text = text.replaceAll("\\s+", " ");
            sb.append(text);
        }
    }
    Assert.assertTrue("UL Content can NOT be found in the node", findSomeUlContent(sb.toString()));
    StringBuffer sbSkip = new StringBuffer();
    NodeWalker walkerSkip = new NodeWalker(parser.getDocument());
    while (walkerSkip.hasNext()) {
        Node currentNode = walkerSkip.nextNode();
        String nodeName = currentNode.getNodeName();
        short nodeType = currentNode.getNodeType();
        if ("ul".equalsIgnoreCase(nodeName)) {
            walkerSkip.skipChildren();
        }
        if (nodeType == Node.TEXT_NODE) {
            String text = currentNode.getNodeValue();
            text = text.replaceAll("\\s+", " ");
            sbSkip.append(text);
        }
    }
    Assert.assertFalse("UL Content can be found in the node", findSomeUlContent(sbSkip.toString()));
}

Example 12 with DOMParser

use of org.apache.xerces.parsers.DOMParser in project mondrian by pentaho.

the class XmlUtil method getParser.

// ////////////////////////////////////////////////////////////////////////
// parse
// ////////////////////////////////////////////////////////////////////////
/**
 * Get your non-cached DOM parser which can be configured to do schema
 * based validation of the instance Document.
 */
public static DOMParser getParser(String schemaLocationPropertyValue, EntityResolver entityResolver, boolean validate) throws SAXNotRecognizedException, SAXNotSupportedException {
    boolean doingValidation = (validate || (schemaLocationPropertyValue != null));
    DOMParser parser = new DOMParser();
    parser.setEntityResolver(entityResolver);
    parser.setErrorHandler(new SaxErrorHandler());
    parser.setFeature(DEFER_NODE_EXPANSION, false);
    parser.setFeature(NAMESPACES_FEATURE_ID, true);
    parser.setFeature(SCHEMA_VALIDATION_FEATURE_ID, doingValidation);
    parser.setFeature(VALIDATION_FEATURE_ID, doingValidation);
    if (schemaLocationPropertyValue != null) {
        parser.setProperty(SCHEMA_LOCATION, schemaLocationPropertyValue.replace('\\', '/'));
    }
    return parser;
}

Example 13 with DOMParser

use of org.apache.xerces.parsers.DOMParser in project cogtool by cogtool.

the class ImportCogToolXML method importXML.

public boolean importXML(Reader input, String imageDirPath, TaskParent taskParent, CognitiveModelGenerator modelGen) throws IOException, SAXException {
    modelGenerator = modelGen;
    // Create a Xerces DOM Parser
    DOMParser parser = new DOMParser();
    // Set the path for loading images
    directoryPath = imageDirPath;
    // Parse the Document and traverse the DOM
    parser.parse(new InputSource(input));
    Document document = parser.getDocument();
    parseFile(document, taskParent);
    if (failedImages.size() > 0) {
        String failedImageString = "Failed to load the following images:";
        Iterator<String> fIter = failedImages.iterator();
        while (fIter.hasNext()) {
            failedImageString += System.getProperty("file.separator") + fIter.next();
        }
        throw new GraphicsUtil.ImageException(failedImageString);
    }
    return true;
}

Example 14 with DOMParser

use of org.apache.xerces.parsers.DOMParser in project ACS by ACS-Community.

the class EbeDocument method load.

/** Load the data from the selected path */
public void load() {
    if (parser == null) {
        parser = new DOMParser();
    }
    try {
        parser.parse(path);
        doc = parser.getDocument();
    } catch (Exception e) {
        e.getMessage();
    }
    nodes.clear();
    // Only one Type
    Node no = doc.getElementsByTagName(EbeDocument.getClassType().name).item(0);
    readNode(no, this);
    // Check for Completions
    NodeList completionNodes = doc.getElementsByTagName(Completion.getClassType().name);
    for (int i = 0; i < completionNodes.getLength(); i++) {
        Node coNo = completionNodes.item(i);
        Completion coObj = new Completion();
        readNode(coNo, coObj);
        this.putNode(coObj);
    }
    NodeList errorNodes = doc.getElementsByTagName(Error.getClassType().name);
    for (int i = 0; i < errorNodes.getLength(); i++) {
        Node erNo = errorNodes.item(i);
        Error erObj = new Error();
        readNode(erNo, erObj);
        Node meNo = erNo.getFirstChild();
        while (meNo != null) {
            if (meNo.getNodeName().matches("Member")) {
                Member meObj = new Member();
                readNode(meNo, meObj);
                erObj.putMember(meObj);
            }
            meNo = meNo.getNextSibling();
        }
        this.putNode(erObj);
    }
}

Example 15 with DOMParser

use of org.apache.xerces.parsers.DOMParser in project ACS by ACS-Community.

the class XmlSeeker method getXmls.

/**
         * Get an Arraylist with the XMLs on the added dirs that conforms with the xsd filename.
         * @param xsd the filename of the xsd to seek inside the XML files
         * @return the XMLs list */
public ArrayList getXmls(String xsd) {
    File[] fileArr;
    ArrayList<File> files = new ArrayList<File>();
    File[] dirArr = new File[dirs.size()];
    dirs.toArray(dirArr);
    AcsFileFinder fileFinder = new AcsFileFinder(dirArr, this, null);
    fileArr = fileFinder.getAllFiles();
    for (int i = 0; i < fileArr.length; i++) {
        DOMParser dp;
        dp = new DOMParser();
        try {
            dp.parse(fileArr[i].getAbsolutePath());
        } catch (Exception e) {
            e.printStackTrace();
        }
        Document doc = dp.getDocument();
        // Hack to support both Errors and Logs 
        // TODO: Please do this thing in a generic way
        Node typeNode = doc.getElementsByTagName("Type").item(0);
        // Type node may not even exist
        if (typeNode != null) {
            NamedNodeMap atributes = typeNode.getAttributes();
            Node schema = atributes.getNamedItem("xsi:schemaLocation");
            if (schema.getNodeValue().contentEquals(xsd))
                files.add(fileArr[i]);
        }
    }
    return (files);
}