Examples with Parser org.ccil.cowan.tagsoup.Parser used on opensource projects

Example 16 with Parser

use of org.ccil.cowan.tagsoup.Parser in project Lucee by lucee.

the class XMLUtilImpl method parse.

/**
 * parse XML/HTML String to a XML DOM representation
 * @param xml XML InputSource
 * @param isHtml is a HTML or XML Object
 * @return parsed Document
 * @throws SAXException
 * @throws IOException
 */
public final Document parse(InputSource xml, InputSource validator, boolean isHtml) throws SAXException, IOException {
    if (!isHtml) {
        DocumentBuilderFactory factory = newDocumentBuilderFactory();
        // print.o(factory);
        if (validator == null) {
            setAttributeEL(factory, NON_VALIDATING_DTD_EXTERNAL, Boolean.FALSE);
            setAttributeEL(factory, NON_VALIDATING_DTD_GRAMMAR, Boolean.FALSE);
        } else {
            setAttributeEL(factory, VALIDATION_SCHEMA, Boolean.TRUE);
            setAttributeEL(factory, VALIDATION_SCHEMA_FULL_CHECKING, Boolean.TRUE);
        }
        factory.setNamespaceAware(true);
        factory.setValidating(validator != null);
        try {
            DocumentBuilder builder = factory.newDocumentBuilder();
            builder.setEntityResolver(new XMLEntityResolverDefaultHandler(validator));
            builder.setErrorHandler(new ThrowingErrorHandler(true, true, false));
            return builder.parse(xml);
        } catch (ParserConfigurationException e) {
            throw new SAXException(e);
        }
    /*DOMParser parser = new DOMParser();
	        print.out("parse");
	        parser.setEntityResolver(new XMLEntityResolverDefaultHandler(validator));
	        parser.parse(xml);
	        return parser.getDocument();*/
    }
    XMLReader reader = new Parser();
    reader.setFeature(Parser.namespacesFeature, true);
    reader.setFeature(Parser.namespacePrefixesFeature, true);
    try {
        Transformer transformer = TransformerFactory.newInstance().newTransformer();
        DOMResult result = new DOMResult();
        transformer.transform(new SAXSource(reader, xml), result);
        return getDocument(result.getNode());
    } catch (Exception e) {
        throw new SAXException(e);
    }
}

Example 17 with Parser

use of org.ccil.cowan.tagsoup.Parser in project knime-core by knime.

the class TipsAndNewsInjector method prepareData.

/**
 * {@inheritDoc}
 */
@Override
protected void prepareData() throws Exception {
    HttpURLConnection conn = (HttpURLConnection) m_tipsAndNewsUrl.openConnection();
    conn.setReadTimeout(5000);
    conn.setConnectTimeout(2000);
    conn.connect();
    // parse tips&tricks from webpage
    XMLReader reader = new Parser();
    reader.setFeature(Parser.namespacesFeature, false);
    reader.setFeature(Parser.namespacePrefixesFeature, false);
    final ClassLoader cl = Thread.currentThread().getContextClassLoader();
    Thread.currentThread().setContextClassLoader(getClass().getClassLoader());
    DOMResult res = new DOMResult();
    try {
        Transformer transformer = m_transformerFactory.newTransformer();
        transformer.transform(new SAXSource(reader, new InputSource(conn.getInputStream())), res);
    } finally {
        Thread.currentThread().setContextClassLoader(cl);
    }
    conn.disconnect();
    XPath xpath = m_xpathFactory.newXPath();
    Node news = (Node) xpath.evaluate("//div[@id='knime-client-news']", res.getNode(), XPathConstants.NODE);
    m_news = checkIfNewsExist(news);
    if (m_news != null) {
        fixRelativeURLs(m_news, xpath);
    }
    m_tips = (Node) xpath.evaluate("//div[@id='col-right']//div[@class='contentWrapper']//div[@class='view-content']", res.getNode(), XPathConstants.NODE);
    if (m_tips != null) {
        fixRelativeURLs(m_tips, xpath);
    }
    m_newsGraphic = (Node) xpath.evaluate("//div[@id='news-graphic']", res.getNode(), XPathConstants.NODE);
    if (m_newsGraphic != null) {
        fixRelativeURLs(m_newsGraphic, xpath);
    }
}

Example 18 with Parser

use of org.ccil.cowan.tagsoup.Parser in project ForPDA by RadiationX.

the class HtmlToSpannedConverter method fromHtml.

/**
 * Returns displayable styled text from the provided HTML string. Any <img> tags in the
 * HTML will use the specified ImageGetter to request a representation of the image (use null
 * if you don't want this) and the specified TagHandler to handle unknown tags (specify null if
 * you don't want this).
 * <p>
 * <p>This uses TagSoup to handle real HTML, including all of the brokenness found in the wild.
 */
public static Spanned fromHtml(String source, int flags, ImageGetter imageGetter, TagHandler tagHandler) {
    Parser parser = new Parser();
    try {
        parser.setProperty(Parser.schemaProperty, HtmlParser.schema);
    } catch (org.xml.sax.SAXNotRecognizedException e) {
        // Should not happen.
        throw new RuntimeException(e);
    } catch (org.xml.sax.SAXNotSupportedException e) {
        // Should not happen.
        throw new RuntimeException(e);
    }
    HtmlToSpannedConverter converter = new HtmlToSpannedConverter(source, imageGetter, tagHandler, parser, flags);
    return converter.convert();
}