Example usage for javax.xml.parsers DocumentBuilderFactory setIgnoringComments

Introduction

In this page you can find the example usage for javax.xml.parsers DocumentBuilderFactory setIgnoringComments.

Prototype


public void setIgnoringComments(boolean ignoreComments)

Source Link

Document

Specifies that the parser produced by this code will ignore comments.

Usage

From source file:ubic.gemma.loader.entrez.pubmed.ESearchXMLParser.java

/**
 * @param is//from   w  w  w.  j  a v a 2  s  .c  o  m
 * @return
 * @throws IOException
 * @throws ParserConfigurationException
 * @throws SAXException
 */
private Document openAndParse(InputStream is) throws IOException, ParserConfigurationException, SAXException {
    if (is.available() == 0) {
        throw new IOException("XML stream contains no data.");
    }

    DocumentBuilderFactory factory = DocumentBuilderFactory.newInstance();
    factory.setIgnoringComments(true);
    // factory.setValidating( true );

    DocumentBuilder builder = factory.newDocumentBuilder();
    Document document = builder.parse(is);
    return document;
}

From source file:ubic.gemma.loader.entrez.pubmed.PubMedXMLParser.java

/**
 * @param is//from ww  w .  ja v  a  2  s.c  o  m
 * @return
 */
public Collection<BibliographicReference> parse(InputStream is) {

    try {
        if (is.available() == 0) {
            throw new IOException("XML stream contains no data.");
        }

        DocumentBuilderFactory factory = DocumentBuilderFactory.newInstance();
        factory.setIgnoringComments(true);
        factory.setValidating(false);
        builder = factory.newDocumentBuilder();
        Document document = builder.parse(is);

        log.debug("done parsing");
        return extractBibRefs(document);
    } catch (IOException e) {
        throw new RuntimeException(e);
    } catch (ParserConfigurationException e) {
        throw new RuntimeException(e);
    } catch (SAXException e) {
        throw new RuntimeException(e);
    }
}

From source file:ubic.gemma.loader.entrez.pubmed.XMLUtils.java

/**
 * @param is/*from ww  w  .  ja  v a2  s  .  c om*/
 * @return
 * @throws IOException
 * @throws ParserConfigurationException
 * @throws SAXException
 */
public static Document openAndParse(InputStream is)
        throws IOException, ParserConfigurationException, SAXException {
    if (is.available() == 0) {
        throw new IOException("XML stream contains no data.");
    }

    DocumentBuilderFactory factory = DocumentBuilderFactory.newInstance();
    factory.setIgnoringComments(true);
    // factory.setValidating( true );

    DocumentBuilder builder = factory.newDocumentBuilder();
    Document document = builder.parse(is);
    return document;
}

From source file:ubic.gemma.web.services.AbstractGemmaEndpoint.java

/**
 * Looks to parse a previously generated xml report that was saved to disk. Returns null if it fails to do so.
 *
 * @param is from an existing xml file//from w w w  .j av  a  2s . c  o  m
 * @return An XML document
 * @throws IOException IO problems
 */
protected Document readReport(InputStream is) throws IOException {

    DocumentBuilderFactory factory = DocumentBuilderFactory.newInstance();
    factory.setIgnoringComments(true);
    factory.setValidating(false);
    Document document;

    try {
        DocumentBuilder builder = factory.newDocumentBuilder();
        document = builder.parse(is);
    } catch (ParserConfigurationException pce) {
        AbstractGemmaEndpoint.log.error("Could not configure parser for reading report.  Error is: " + pce);
        throw (new RuntimeException(pce));
    } catch (SAXException se) {
        AbstractGemmaEndpoint.log.error("Could not parse report Error is: " + se);
        throw (new RuntimeException(se));

    }

    return document;

}

From source file:uk.co.tfd.symplectic.harvester.XmlAide.java

public static Document loadXmlDocument(String url)
        throws MalformedURLException, SAXException, IOException, ParserConfigurationException {
    DocumentBuilderFactory docBuildFactory = DocumentBuilderFactory.newInstance();
    docBuildFactory.setIgnoringComments(true);

    String xmlDoc = null;//from  w  w w.  j  a v a  2 s  .co m
    if (url.startsWith("http")) {
        xmlDoc = ConcurrentHttpFetch.get(url);
    } else {
        xmlDoc = WebAide.getURLContents(url);
    }
    // doing this fixes makes it work with UTF8 chars
    return docBuildFactory.newDocumentBuilder().parse(new InputSource(new StringReader(xmlDoc)));
}

From source file:uk.me.jeffsutton.pojogen.SimplePOJO.java

public Document parse(BufferedReader xml) throws IOException, SAXException, ParserConfigurationException {
    String file = "";
    try {//from  w  w w .j av a 2s.co m
        String str;
        while ((str = xml.readLine()) != null) {
            file += str;
        }
    } catch (Exception e) {
        e.printStackTrace();
    }

    file = file.replaceAll("<!DOCTYPE((.|\n|\r)*?)\">", "");

    // convert String into InputStream
    InputStream is = new ByteArrayInputStream(file.getBytes());

    DocumentBuilderFactory dbf = DocumentBuilderFactory.newInstance();
    dbf.setFeature("http://apache.org/xml/features/nonvalidating/load-dtd-grammar", false);
    dbf.setFeature("http://apache.org/xml/features/nonvalidating/load-external-dtd", false);
    dbf.setFeature("http://apache.org/xml/features/disallow-doctype-decl", true);
    dbf.setFeature("http://xml.org/sax/features/validation", false);
    dbf.setNamespaceAware(false);
    dbf.setIgnoringComments(true);
    dbf.setValidating(false);
    dbf.setXIncludeAware(true);

    return dbf.newDocumentBuilder().parse(is);
}