Example usage for javax.xml.parsers DocumentBuilderFactory setIgnoringElementContentWhitespace

List of usage examples for javax.xml.parsers DocumentBuilderFactory setIgnoringElementContentWhitespace

  1. HOME
  2. Java
  3. javax
  4. javax.xml.parsers.*
  5. DocumentBuilderFactory
  6. setIgnoringElementContentWhitespace

Introduction

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

Prototype


public void setIgnoringElementContentWhitespace(boolean whitespace)

Source Link

Document

Specifies that the parsers created by this factory must eliminate whitespace in element content (sometimes known loosely as 'ignorable whitespace') when parsing XML documents (see XML Rec 2.10).

Usage

From source file:org.codice.ddf.security.idp.server.IdpEndpointTest.java

public static Document readXml(InputStream is) throws SAXException, IOException, ParserConfigurationException {
    DocumentBuilderFactory dbf = DocumentBuilderFactory.newInstance();

    dbf.setValidating(false);//  ww w . j a  v a 2 s  .c o m
    dbf.setIgnoringComments(false);
    dbf.setIgnoringElementContentWhitespace(true);
    dbf.setNamespaceAware(true);

    DocumentBuilder db = dbf.newDocumentBuilder();
    db.setEntityResolver(new DOMUtils.NullResolver());

    return db.parse(is);
}

From source file:org.codice.ddf.security.servlet.expiry.SessionManagementServiceTest.java

private static Document readXml(InputStream is) throws SAXException, IOException, ParserConfigurationException {
    DocumentBuilderFactory dbf = DocumentBuilderFactory.newInstance();

    dbf.setValidating(false);/* w ww . ja  va2s.  c  o  m*/
    dbf.setIgnoringComments(false);
    dbf.setIgnoringElementContentWhitespace(true);
    dbf.setNamespaceAware(true);

    DocumentBuilder db = dbf.newDocumentBuilder();
    db.setEntityResolver(new DOMUtils.NullResolver());

    return db.parse(is);
}

From source file:org.cruxframework.crux.core.declarativeui.ViewProcessor.java

/**
 * Initializes the static resources/*w ww  .  ja  va  2  s  .  c  o m*/
 */
private static void init() {
    if (documentBuilder == null) {
        lock.lock();

        if (documentBuilder == null) {
            try {
                DocumentBuilderFactory builderFactory = DocumentBuilderFactory.newInstance();
                builderFactory.setNamespaceAware(true);
                builderFactory.setIgnoringComments(true);
                builderFactory.setIgnoringElementContentWhitespace(true);

                documentBuilder = builderFactory.newDocumentBuilder();
                documentBuilder.setEntityResolver(new EntityResolver() {
                    @Override
                    public InputSource resolveEntity(String publicId, String systemId)
                            throws SAXException, IOException {
                        if (systemId.contains("crux-view.dtd")) {
                            return new InputSource(new ByteArrayInputStream(getValidEntities().getBytes()));
                        } else {
                            return null;
                        }
                    }

                    private String getValidEntities() {
                        StringBuffer sb = new StringBuffer();
                        sb.append("<!ENTITY quot    \"&#34;\">");
                        sb.append("<!ENTITY amp     \"&#38;\">");
                        sb.append("<!ENTITY apos    \"&#39;\">");
                        sb.append("<!ENTITY lt      \"&#60;\">");
                        sb.append("<!ENTITY gt      \"&#62;\">");
                        sb.append("<!ENTITY nbsp    \"&#160;\">");
                        return sb.toString();
                    }
                });

                initializePreProcessors();
            } catch (Throwable e) {
                log.error("Error initializing cruxToHtmlTransformer.", e);
            } finally {
                lock.unlock();
            }
        }
    }
}

From source file:org.cytobank.acs.core.TableOfContents.java

/**
 * <p>Creates a DocumentBuilder with Cytobank's preferred security settings
 * applied to it. Specifically turning off external entities and external
 * DTDs to prevent External Entity Exploits (XXE)</p>
 *
 * @throws ParserConfigurationException/*  w  w  w  . j a  va2 s.c  o m*/
 * @return DocumentBuilder
 */
protected DocumentBuilder getDocumentBuilder() throws ParserConfigurationException {

    DocumentBuilderFactory dbf = DocumentBuilderFactory.newInstance();

    DocumentBuilder db = null;

    String FEATURE = null;

    // This is the PRIMARY defense. If DTDs (doctypes) are disallowed, almost all XML entity attacks are prevented
    // Xerces 2 only - http://xerces.apache.org/xerces2-j/features.html#disallow-doctype-decl
    FEATURE = "http://apache.org/xml/features/disallow-doctype-decl";
    dbf.setFeature(FEATURE, true);

    // If you can't completely disable DTDs, then at least do the following:
    // Xerces 1 - http://xerces.apache.org/xerces-j/features.html#external-general-entities
    // Xerces 2 - http://xerces.apache.org/xerces2-j/features.html#external-general-entities
    // JDK7+ - http://xml.org/sax/features/external-general-entities
    FEATURE = "http://xml.org/sax/features/external-general-entities";
    dbf.setFeature(FEATURE, false);

    // Xerces 1 - http://xerces.apache.org/xerces-j/features.html#external-parameter-entities
    // Xerces 2 - http://xerces.apache.org/xerces2-j/features.html#external-parameter-entities
    // JDK7+ - http://xml.org/sax/features/external-parameter-entities
    FEATURE = "http://xml.org/sax/features/external-parameter-entities";
    dbf.setFeature(FEATURE, false);

    // Disable external DTDs as well
    FEATURE = "http://apache.org/xml/features/nonvalidating/load-external-dtd";
    dbf.setFeature(FEATURE, false);

    // and these as well, per Timothy Morgan's 2014 paper: "XML Schema, DTD, and Entity Attacks" (see reference below)
    dbf.setXIncludeAware(false);
    dbf.setExpandEntityReferences(false);

    // And, per Timothy Morgan: "If for some reason support for inline DOCTYPEs are a requirement, then
    // ensure the entity settings are disabled (as shown above) and beware that SSRF attacks
    // (http://cwe.mitre.org/data/definitions/918.html) and denial
    // of service attacks (such as billion laughs or decompression bombs via "jar:") are a risk."

    boolean namespaceAware = true;
    boolean xsdValidate = false;
    boolean ignoreWhitespace = false;
    boolean ignoreComments = false;
    boolean putCDATAIntoText = false;
    boolean createEntityRefs = false;

    dbf.setNamespaceAware(namespaceAware);
    dbf.setValidating(xsdValidate);
    dbf.setIgnoringComments(ignoreComments);
    dbf.setIgnoringElementContentWhitespace(ignoreWhitespace);
    dbf.setCoalescing(putCDATAIntoText);
    dbf.setExpandEntityReferences(createEntityRefs);

    db = dbf.newDocumentBuilder();

    return db;

}

From source file:org.deegree.portal.owswatch.validator.AbstractValidator.java

/**
 * Creates a new instance of DocumentBuilder
 *
 * @return DocumentBuilder// ww w. j  a va 2  s .  c om
 * @throws IOException
 */
protected DocumentBuilder instantiateParser() throws IOException {

    DocumentBuilder parser = null;

    try {
        DocumentBuilderFactory fac = DocumentBuilderFactory.newInstance();
        fac.setNamespaceAware(true);
        fac.setValidating(false);
        fac.setIgnoringElementContentWhitespace(false);
        parser = fac.newDocumentBuilder();
        return parser;
    } catch (ParserConfigurationException e) {
        throw new IOException("Unable to initialize DocumentBuilder: " + e.getMessage());
    }
}

From source file:org.drugis.addis.util.ConvertDiabetesDatasetUtil.java

private Document getPubMedXML(PubMedIdList pubmed)
        throws ParserConfigurationException, IOException, SAXException {
    String id = pubmed.get(0).getId();
    String url = PubMedIDRetriever.PUBMED_API + "efetch.fcgi?db=pubmed&id=" + id + "&retmode=xml";
    DocumentBuilderFactory dbf = DocumentBuilderFactory.newInstance();
    dbf.setValidating(false);/*from  w  w w  .ja  v  a 2 s  .c  o m*/
    dbf.setNamespaceAware(false);
    dbf.setIgnoringElementContentWhitespace(true);
    DocumentBuilder db = dbf.newDocumentBuilder();
    InputStream openStream = PubMedIDRetriever.openUrl(url);
    Document doc = db.parse(openStream);
    return doc;
}

From source file:org.dspace.app.sfx.SFXFileReader.java

/** Parses XML file and returns XML document.
 * @param fileName XML file to parse//  w  w w . j a  v  a  2 s .  c  om
 * @return XML document or <B>null</B> if error occured. The error is caught and logged.
 */

public static Document parseFile(String fileName) {
    log.info("Parsing XML file... " + fileName);
    DocumentBuilder docBuilder;
    Document doc = null;
    DocumentBuilderFactory docBuilderFactory = DocumentBuilderFactory.newInstance();
    docBuilderFactory.setIgnoringElementContentWhitespace(true);
    try {
        docBuilder = docBuilderFactory.newDocumentBuilder();
    } catch (ParserConfigurationException e) {
        log.error("Wrong parser configuration: " + e.getMessage());
        return null;
    }
    File sourceFile = new File(fileName);
    try {
        doc = docBuilder.parse(sourceFile);
    } catch (SAXException e) {
        log.error("Wrong XML file structure: " + e.getMessage());
        return null;
    } catch (IOException e) {
        log.error("Could not read source file: " + e.getMessage());
    }
    log.info("XML file parsed");
    return doc;
}

From source file:org.dspace.app.sfx.SFXFileReaderServiceImpl.java

@Override
public Document parseFile(String fileName) {
    log.info("Parsing XML file... " + fileName);
    DocumentBuilder docBuilder;//from  www  .j a  v  a 2s  . c om
    Document doc = null;
    DocumentBuilderFactory docBuilderFactory = DocumentBuilderFactory.newInstance();
    docBuilderFactory.setIgnoringElementContentWhitespace(true);
    try {
        docBuilder = docBuilderFactory.newDocumentBuilder();
    } catch (ParserConfigurationException e) {
        log.error("Wrong parser configuration: " + e.getMessage());
        return null;
    }
    File sourceFile = new File(fileName);
    try {
        doc = docBuilder.parse(sourceFile);
    } catch (SAXException e) {
        log.error("Wrong XML file structure: " + e.getMessage());
        return null;
    } catch (IOException e) {
        log.error("Could not read source file: " + e.getMessage());
    }
    log.info("XML file parsed");
    return doc;
}

From source file:org.dspace.app.sherpa.SHERPAResponse.java

public SHERPAResponse(InputStream xmlData) {
    try {/* www  .  j av a2 s .  c o  m*/
        DocumentBuilderFactory factory = DocumentBuilderFactory.newInstance();
        factory.setValidating(false);
        factory.setIgnoringComments(true);
        factory.setIgnoringElementContentWhitespace(true);

        DocumentBuilder db = factory.newDocumentBuilder();
        Document inDoc = db.parse(xmlData);

        Element xmlRoot = inDoc.getDocumentElement();
        Element headersElement = XMLUtils.getSingleElement(xmlRoot, "header");
        Element journalsElement = XMLUtils.getSingleElement(xmlRoot, "journals");
        Element publishersElement = XMLUtils.getSingleElement(xmlRoot, "publishers");

        message = XMLUtils.getElementValue(headersElement, "message");

        if (StringUtils.isNotBlank(message)) {
            error = true;
            return;
        }

        license = XMLUtils.getElementValue(headersElement, "license");
        licenseURL = XMLUtils.getElementValue(headersElement, "licenseurl");
        disclaimer = XMLUtils.getElementValue(headersElement, "disclaimer");

        List<Element> journalsList = XMLUtils.getElementList(journalsElement, "journal");
        List<Element> publishersList = XMLUtils.getElementList(publishersElement, "publisher");

        if (journalsList != null) {
            journals = new LinkedList<SHERPAJournal>();
            for (Element journalElement : journalsList) {
                journals.add(new SHERPAJournal(XMLUtils.getElementValue(journalElement, "jtitle"),
                        XMLUtils.getElementValue(journalElement, "issn"),
                        XMLUtils.getElementValue(journalElement, "zetopub"),
                        XMLUtils.getElementValue(journalElement, "romeopub")));
            }
        }

        if (publishersList != null) {
            publishers = new LinkedList<SHERPAPublisher>();
            for (Element publisherElement : publishersList) {
                Element preprintsElement = XMLUtils.getSingleElement(publisherElement, "preprints");
                Element preprintsRestrictionElement = XMLUtils.getSingleElement(publisherElement,
                        "prerestrictions");

                Element postprintsElement = XMLUtils.getSingleElement(publisherElement, "postprints");
                Element postprintsRestrictionElement = XMLUtils.getSingleElement(publisherElement,
                        "postrestrictions");

                Element pdfversionElement = XMLUtils.getSingleElement(publisherElement, "pdfversion");
                Element pdfversionRestrictionElement = XMLUtils.getSingleElement(publisherElement,
                        "pdfrestrictions");

                Element conditionsElement = XMLUtils.getSingleElement(publisherElement, "conditions");
                Element paidaccessElement = XMLUtils.getSingleElement(publisherElement, "paidaccess");

                Element copyrightlinksElement = XMLUtils.getSingleElement(publisherElement, "copyrightlinks");

                publishers.add(new SHERPAPublisher(XMLUtils.getElementValue(publisherElement, "name"),
                        XMLUtils.getElementValue(publisherElement, "alias"),
                        XMLUtils.getElementValue(publisherElement, "homeurl"),

                        XMLUtils.getElementValue(preprintsElement, "prearchiving"),
                        XMLUtils.getElementValueList(preprintsRestrictionElement, "prerestriction"),

                        XMLUtils.getElementValue(postprintsElement, "postarchiving"),
                        XMLUtils.getElementValueList(postprintsRestrictionElement, "postrestriction"),

                        XMLUtils.getElementValue(pdfversionElement, "pdfarchiving"),
                        XMLUtils.getElementValueList(pdfversionRestrictionElement, "pdfrestriction"),

                        XMLUtils.getElementValueList(conditionsElement, "condition"),
                        XMLUtils.getElementValue(paidaccessElement, "paidaccessurl"),
                        XMLUtils.getElementValue(paidaccessElement, "paidaccessname"),
                        XMLUtils.getElementValue(paidaccessElement, "paidaccessnotes"),
                        XMLUtils.getElementValueArrayList(copyrightlinksElement, "copyrightlink",
                                "copyrightlinktext", "copyrightlinkurl"),
                        XMLUtils.getElementValue(publisherElement, "romeocolour"),
                        XMLUtils.getElementValue(publisherElement, "dateadded"),
                        XMLUtils.getElementValue(publisherElement, "dateupdated")));
            }
        }
    } catch (Exception e) {
        error = true;
    }
}

From source file:org.dspace.app.util.DCInputsReader.java

private void buildInputs(String fileName) throws DCInputsReaderException {
    formDefns = new HashMap<String, List<Map<String, String>>>();
    valuePairs = new HashMap<String, List<String>>();

    String uri = "file:" + new File(fileName).getAbsolutePath();

    try {/*from   w ww. ja v a  2  s.  c o  m*/
        DocumentBuilderFactory factory = DocumentBuilderFactory.newInstance();
        factory.setValidating(false);
        factory.setIgnoringComments(true);
        factory.setIgnoringElementContentWhitespace(true);

        DocumentBuilder db = factory.newDocumentBuilder();
        Document doc = db.parse(uri);
        doNodes(doc);
        checkValues();
    } catch (FactoryConfigurationError fe) {
        throw new DCInputsReaderException("Cannot create Submission form parser", fe);
    } catch (Exception e) {
        throw new DCInputsReaderException("Error creating submission forms: " + e);
    }
}