Example usage for org.jsoup.parser Parser parseXmlFragment

Introduction

In this page you can find the example usage for org.jsoup.parser Parser parseXmlFragment.

Prototype

public static List<Node> parseXmlFragment(String fragmentXml, String baseUri) 

Source Link

Document

Parse a fragment of XML into a list of nodes.

Usage

From source file:com.ufukuzun.myth.dialect.bean.Myth.java

private Document parse(String html) {
    Document document = new Document("");

    List<Node> nodes = Parser.parseXmlFragment(html, "");
    if (!nodes.isEmpty()) {
        document.appendChild(nodes.get(0));
    }/*from   ww w  .  j  av  a 2s.  com*/

    return document;
}

---

From source file:org.dswarm.xmlenhancer.XMLEnhancer.java

public static void enhanceXML(final String inputFileName, final String outputFileName) throws IOException {

    final Path inputFilePath = Paths.get(inputFileName);
    final byte[] inputBytes = Files.readAllBytes(inputFilePath);
    final String inputString = new String(inputBytes, StandardCharsets.UTF_8);

    final List<Node> nodes = Parser.parseXmlFragment(inputString, DUMMY_BASE_URI);

    enhanceNodes(nodes);/*from  ww w  .  jav a 2 s  .  c  om*/

    final Path outputFilePath = Paths.get(outputFileName);
    final String outResource = outputFilePath.toString();

    final PrintWriter out = new PrintWriter(outResource, UTF_8);

    nodes.forEach(node -> unescapeEntity(out, node));

    out.flush();
    out.close();
}

---

From source file:org.structr.web.importer.Importer.java

/**
 * Parse the code previously read by {@link Importer#readPage()} and treat it as page fragment.
 *
 * @param fragment/*from w w w  .  ja v  a 2s. c  o m*/
 * @return
 * @throws FrameworkException
 */
public boolean parse(final boolean fragment) throws FrameworkException {

    init();

    if (StringUtils.isNotBlank(code)) {

        if (!isDeployment) {
            logger.info("##### Start parsing code for page {} #####", new Object[] { name });
        } else {

            // a trailing slash to all void/self-closing tags so the XML parser can parse it correctly
            code = code.replaceAll(
                    "<(area|base|br|col|command|embed|hr|img|input|keygen|link|meta|param|source|track|wbr)([^>]*)>",
                    "<$1$2/>");
        }

        if (fragment) {

            if (isDeployment) {

                final List<Node> nodeList = Parser.parseXmlFragment(code, "");
                parsedDocument = Document.createShell("");
                final Element body = parsedDocument.body();
                final Node[] nodes = nodeList.toArray(new Node[nodeList.size()]);

                for (int i = nodes.length - 1; i > 0; i--) {
                    nodes[i].remove();
                }

                for (Node node : nodes) {
                    body.appendChild(node);
                }

            } else {

                parsedDocument = Jsoup.parseBodyFragment(code);
            }

        } else {

            if (isDeployment) {

                parsedDocument = Jsoup.parse(code, "", Parser.xmlParser());

            } else {

                parsedDocument = Jsoup.parse(code);
            }

        }

    } else {

        if (!isDeployment) {
            logger.info("##### Start fetching {} for page {} #####", new Object[] { address, name });
        }

        code = HttpHelper.get(address);
        parsedDocument = Jsoup.parse(code);

    }

    return true;

}

---